{"total":215,"rows":[{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553,"area":"mechinterp"},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"id":"2501.18052","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","created":"2025-01-29","cited_by_count":80,"area":"diffusion"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2408.00113","title":"Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models","created":"2024-07-31","cited_by_count":51,"area":"mechinterp"},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"area":"mechinterp"},{"id":"2410.14670","title":"Decomposing The Dark Matter of Sparse Autoencoders","created":"2024-10-18","cited_by_count":45,"area":"mechinterp"},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2410.08201","title":"Efficient Dictionary Learning with Switch Sparse Autoencoders","created":"2024-10-10","cited_by_count":39,"area":"mechinterp"},{"id":"2502.08524","title":"LLM Pretraining with Continuous Concepts","created":"2025-02-12","cited_by_count":36,"area":"lr"},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2411.16725","title":"$\\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models","created":"2024-11-23","cited_by_count":30,"area":"diffusion"},{"id":"2410.06981","title":"Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders","created":"2024-10-09","cited_by_count":27,"area":"mechinterp"},{"id":"2510.07364","title":"Base Models Know How to Reason, Thinking Models Learn When","created":"2025-10-08","cited_by_count":27,"area":"lr"},{"id":"2502.04382","title":"Sparse Autoencoders for Hypothesis Generation","created":"2025-02-05","cited_by_count":26,"area":"mechinterp"},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2503.08200","title":"Route Sparse Autoencoder to Interpret Large Language Models","created":"2025-03-11","cited_by_count":26,"area":"mechinterp"},{"id":"2411.01220","title":"Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders","created":"2024-11-02","cited_by_count":25,"area":"mechinterp"},{"id":"2502.06755","title":"Interpretable and Testable Vision Features via Sparse Autoencoders","created":"2025-02-10","cited_by_count":25,"area":"mechinterp"},{"id":"2503.07639","title":"Mixture of Experts Made Intrinsically Interpretable","created":"2025-03-05","cited_by_count":24,"area":"moe"},{"id":"2306.17638","title":"Geometric Autoencoders -- What You See is What You Decode","created":"2023-06-30","cited_by_count":23,"area":null},{"id":"2408.00657","title":"Disentangling Dense Embeddings with Sparse Autoencoders","created":"2024-08-01","cited_by_count":23,"area":"mechinterp"},{"id":"2410.11179","title":"Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs","created":"2024-10-15","cited_by_count":23,"area":"mechinterp"},{"id":"2107.11191","title":"Regularising Inverse Problems with Generative Machine Learning Models","created":"2021-07-22","cited_by_count":22,"area":null},{"id":"2504.15473","title":"Emergence and Evolution of Interpretable Concepts in Diffusion Models","created":"2025-04-21","cited_by_count":22,"area":"diffusion"},{"id":"2502.15576","title":"Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders","created":"2025-02-21","cited_by_count":21,"area":"mechinterp"},{"id":"2203.06514","title":"Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations","created":"2022-03-12","cited_by_count":19,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2409.04185","title":"Residual Stream Analysis with Multi-Layer SAEs","created":"2024-09-06","cited_by_count":19,"area":"mechinterp"},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19,"area":"mechinterp"},{"id":"2411.13117","title":"Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders","created":"2024-11-20","cited_by_count":18,"area":"mechinterp"},{"id":"2106.02923","title":"Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization","created":"2021-06-05","cited_by_count":17,"area":null},{"id":"2407.03921","title":"Concept Bottleneck Models Without Predefined Concepts","created":"2024-07-04","cited_by_count":17,"area":null},{"id":"2412.08890","title":"Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries","created":"2024-12-12","cited_by_count":17,"area":"inference"},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2503.07050","title":"TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation","created":"2025-03-10","cited_by_count":16,"area":"diffusion"},{"id":"2112.13896","title":"Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks","created":"2021-12-27","cited_by_count":15,"area":null},{"id":"2506.15963","title":"On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy","created":"2025-06-19","cited_by_count":14,"area":"mechinterp"},{"id":"2502.03032","title":"Analyze Feature Flow to Enhance Interpretation and Steering in Language Models","created":"2025-02-05","cited_by_count":13,"area":"mechinterp"},{"id":"2505.18186","title":"Discovering and Steering Interpretable Concepts in Large Generative Music Models","created":"2025-05-18","cited_by_count":13,"area":"mechinterp"},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2509.21379","title":"SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders","created":"2025-09-23","cited_by_count":10,"area":"diffusion"},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2411.02124","title":"Adaptive Sparse Allocation with Mutual Choice & Feature Choice Sparse Autoencoders","created":"2024-11-04","cited_by_count":9,"area":"mechinterp"},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2507.23221","title":"A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2503.09446","title":"Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models","created":"2025-03-12","cited_by_count":8,"area":"diffusion"},{"id":"2503.24277","title":"Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality","created":"2025-03-31","cited_by_count":8,"area":"mechinterp"},{"id":"2507.12464","title":"CytoSAE: Interpretable Cell Embeddings for Hematology","created":"2025-07-16","cited_by_count":8,"area":"mechinterp"},{"id":"2109.10656","title":"Vehicle Behavior Prediction and Generalization Using Imbalanced Learning Techniques","created":"2021-09-22","cited_by_count":7,"area":null},{"id":"2501.19066","title":"Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations","created":"2025-01-31","cited_by_count":7,"area":"mechinterp"},{"id":"2501.19406","title":"Low-Rank Adapting Models for Sparse Autoencoders","created":"2025-01-31","cited_by_count":7,"area":"mechinterp"},{"id":"2206.03698","title":"What do we learn? Debunking the Myth of Unsupervised Outlier Detection","created":"2022-06-08","cited_by_count":6,"area":null},{"id":"2503.11232","title":"PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders","created":"2025-03-14","cited_by_count":6,"area":"mechinterp"},{"id":"2505.15524","title":"Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs","created":"2025-05-21","cited_by_count":6,"area":"mechinterp"},{"id":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2509.05291","title":"Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining","created":"2025-09-05","cited_by_count":6,"area":null},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2103.14528","title":"Model-based Reconstruction with Learning: From Unsupervised to Supervised and Beyond","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2502.14133","title":"Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification","created":"2025-02-19","cited_by_count":5,"area":"mechinterp"},{"id":"2503.06394","title":"How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders","created":"2025-03-09","cited_by_count":5,"area":"mechinterp"},{"id":"2503.15573","title":"Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2506.02204","title":"BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2509.24510","title":"Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2605.13930","title":"Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders","created":"2026-05-13","cited_by_count":5,"area":"mechinterp"},{"id":"2107.10030","title":"Differentiable Feature Selection, a Reparameterization Approach","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2208.10847","title":"Latent Variable Models in the Era of Industrial Big Data: Extension and Beyond","created":"2022-08-23","cited_by_count":4,"area":null},{"id":"2405.14270","title":"Sparse $L^1$-Autoencoders for Scientific Data Compression","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2408.03388","title":"A Non-negative VAE:the Generalized Gamma Belief Network","created":"2024-08-06","cited_by_count":4,"area":null},{"id":"2410.06993","title":"Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2412.16247","title":"Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models","created":"2024-12-20","cited_by_count":4,"area":null},{"id":"2505.11388","title":"The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2505.24473","title":"Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy","created":"2025-05-30","cited_by_count":4,"area":"mechinterp"},{"id":"2510.03186","title":"Superposition disentanglement of neural representations reveals hidden alignment","created":"2025-10-03","cited_by_count":4,"area":"mechinterp"},{"id":"2603.02952","title":"Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPT","created":"2026-03-03","cited_by_count":4,"area":"mechinterp"},{"id":"2605.29889","title":"Where Do Apparent LLM Clinical Triage Failures Arise? Localizing the Multiple-Choice Format Effect","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2606.07878","title":"Still: Amortized KV Cache Compaction in a Single Forward Pass","created":"2026-06-05","cited_by_count":4,"area":"inference"},{"id":"2103.07674","title":"Efficient Sparse Artificial Neural Networks","created":"2021-03-13","cited_by_count":3,"area":null},{"id":"2112.09214","title":"Sparse Coding with Multi-Layer Decoders using Variance Regularization","created":"2021-12-16","cited_by_count":3,"area":null},{"id":"2410.12101","title":"The Persian Rug: solving toy models of superposition using large-scale symmetries","created":"2024-10-15","cited_by_count":3,"area":"mechinterp"},{"id":"2505.17769","title":"Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2506.04859","title":"Sparse Autoencoders, Again?","created":"2025-06-05","cited_by_count":3,"area":"mechinterp"},{"id":"2507.16069","title":"Interpreting CFD Surrogates through Sparse Autoencoders","created":"2025-07-21","cited_by_count":3,"area":"mechinterp"},{"id":"2507.20973","title":"Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder","created":"2025-07-28","cited_by_count":3,"area":"diffusion"},{"id":"2507.22918","title":"Semantic Convergence: Investigating Shared Representations Across Scaled LLMs","created":"2025-07-21","cited_by_count":3,"area":"mechinterp"},{"id":"2509.03738","title":"Mechanistic Interpretability with Sparse Autoencoder Neural Operators","created":"2025-09-03","cited_by_count":3,"area":"mechinterp"},{"id":"2509.25045","title":"Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2511.16309","title":"Sparse Autoencoders are Topic Models","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2512.05534","title":"A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima","created":"2025-12-05","cited_by_count":3,"area":"mechinterp"},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2602.00621","title":"Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering","created":"2026-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2602.12026","title":"Protein Circuit Tracing via Cross-layer Transcoders","created":"2026-02-12","cited_by_count":3,"area":"mechinterp"},{"id":"2605.10971","title":"Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models","created":"2026-05-08","cited_by_count":3,"area":"diffusion"},{"id":"2606.01479","title":"Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech","created":"2026-05-31","cited_by_count":3,"area":"mechinterp"}],"next_cursor":"100"}