{"total":143,"rows":[{"id":"2505.18235","title":"The Origins of Representation Manifolds in Large Language Models","created":"2025-05-23","cited_by_count":51,"area":"mechinterp"},{"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":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19,"area":"mechinterp"},{"id":"2511.05541","title":"Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability","created":"2025-10-30","cited_by_count":18,"area":"mechinterp"},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2505.11756","title":"Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders","created":"2025-05-16","cited_by_count":16,"area":"mechinterp"},{"id":"2505.20254","title":"Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs","created":"2025-05-26","cited_by_count":14,"area":"mechinterp"},{"id":"2506.01197","title":"Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures","created":"2025-06-01","cited_by_count":14,"area":"mechinterp"},{"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":"2508.16560","title":"Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders","created":"2025-08-22","cited_by_count":14,"area":"mechinterp"},{"id":"2602.14111","title":"Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?","created":"2026-02-15","cited_by_count":14,"area":"mechinterp"},{"id":"2602.14687","title":"SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data","created":"2026-02-16","cited_by_count":11,"area":"synth"},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2510.05081","title":"SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder","created":"2025-10-06","cited_by_count":9,"area":"diffusion"},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2509.22033","title":"OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features","created":"2025-09-26","cited_by_count":8,"area":"mechinterp"},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2512.13568","title":"Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability","created":"2025-12-15","cited_by_count":7,"area":"mechinterp"},{"id":"2509.18127","title":"Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework","created":"2025-09-11","cited_by_count":6,"area":"mechinterp"},{"id":"2511.06494","title":"Route Experts by Sequence, not by Token","created":"2025-11-09","cited_by_count":6,"area":"moe"},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2601.05437","title":"Tracing Moral Foundations in Large Language Models","created":"2026-01-09","cited_by_count":6,"area":"mechinterp"},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2602.11881","title":"From Atoms to Trees: Building a Structured Feature Forest with Hierarchical Sparse Autoencoders","created":"2026-02-12","cited_by_count":6,"area":"mechinterp"},{"id":"2602.24014","title":"Interpretable Debiasing of Vision-Language Models for Social Fairness","created":"2026-02-27","cited_by_count":6,"area":"lr"},{"id":"2510.16820","title":"Finding Manifolds With Bilinear Autoencoders","created":"2025-10-19","cited_by_count":5,"area":"mechinterp"},{"id":"2603.04198","title":"Stable and Steerable Sparse Autoencoders with Weight Regularization","created":"2026-03-04","cited_by_count":5,"area":"mechinterp"},{"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":"2509.06938","title":"From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2509.23717","title":"Measuring Sparse Autoencoder Feature Sensitivity","created":"2025-09-28","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":"2512.24975","title":"Attribution-Guided Distillation of Matryoshka Sparse Autoencoders","created":"2025-12-31","cited_by_count":4,"area":"mechinterp"},{"id":"2601.22012","title":"Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability","created":"2026-01-29","cited_by_count":4,"area":"mechinterp"},{"id":"2605.07922","title":"Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders","created":"2026-05-08","cited_by_count":4,"area":"mechinterp"},{"id":"2605.18229","title":"Are Sparse Autoencoder Benchmarks Reliable?","created":"2026-05-18","cited_by_count":4,"area":"mechinterp"},{"id":"2606.06333","title":"Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability","created":"2026-06-04","cited_by_count":4,"area":"mechinterp"},{"id":"2606.11722","title":"ICA Lens: Interpreting Language Models Without Training Another Dictionary","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2505.16077","title":"Ensembling Sparse Autoencoders","created":"2025-05-21","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":"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":"2602.01322","title":"PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding","created":"2026-02-01","cited_by_count":3,"area":"mechinterp"},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2605.14694","title":"The Rate-Distortion-Polysemanticity Tradeoff in SAEs","created":"2026-05-14","cited_by_count":3,"area":"mechinterp"},{"id":"2606.06664","title":"Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers","created":"2026-06-04","cited_by_count":3,"area":"mechinterp"},{"id":"2505.18441","title":"DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces","created":"2025-05-24","cited_by_count":2,"area":"mechinterp"},{"id":"2505.19333","title":"Evaluating Steering Techniques using Human Similarity Judgments","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2505.21399","title":"Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2507.12950","title":"Insights into a radiology-specialised multimodal large language model with sparse autoencoders","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"id":"2509.00691","title":"CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders","created":"2025-08-31","cited_by_count":2,"area":"mechinterp"},{"id":"2510.06378","title":"Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.23749","title":"Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2511.06048","title":"Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts","created":"2025-11-08","cited_by_count":2,"area":"mechinterp"},{"id":"2512.08077","title":"Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders","created":"2025-12-08","cited_by_count":2,"area":"mechinterp"},{"id":"2512.18452","title":"Secret mixtures of experts inside your LLM","created":"2025-12-20","cited_by_count":2,"area":"moe"},{"id":"2605.12122","title":"Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning","created":"2026-05-12","cited_by_count":2,"area":"diffusion"},{"id":"2605.12874","title":"Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features","created":"2026-05-13","cited_by_count":2,"area":"mechinterp"},{"id":"2605.20612","title":"Matryoshka Concept Bottleneck Models","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2606.07654","title":"MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework","created":"2026-06-03","cited_by_count":2,"area":"mllm"},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2506.05239","title":"Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit","created":"2025-06-05","cited_by_count":1,"area":"mechinterp"},{"id":"2511.17735","title":"Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders","created":"2025-11-21","cited_by_count":1,"area":"mechinterp"},{"id":"2512.02194","title":"Enforcing Orderedness to Improve Feature Consistency","created":"2025-12-01","cited_by_count":1,"area":"mechinterp"},{"id":"2512.18930","title":"LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer","created":"2025-12-22","cited_by_count":1,"area":"mechinterp"},{"id":"2601.22447","title":"Beyond Activation Patterns: A Weight-Based Out-of-Context Explanation of Sparse Autoencoder Features","created":"2026-01-30","cited_by_count":1,"area":"mechinterp"},{"id":"2602.05183","title":"Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning","created":"2026-02-05","cited_by_count":1,"area":"agents"},{"id":"2602.12403","title":"MonoLoss: A Training Objective for Interpretable Monosemantic Representations","created":"2026-02-12","cited_by_count":1,"area":"mechinterp"},{"id":"2602.20904","title":"Transcoder Adapters for Reasoning-Model Diffing","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2603.03319","title":"Automated Concept Discovery for LLM-as-a-Judge Preference Analysis","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2604.06495","title":"Improving Robustness In Sparse Autoencoders via Masked Regularization","created":"2026-04-07","cited_by_count":1,"area":"mechinterp"},{"id":"2605.06610","title":"SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders","created":"2026-05-07","cited_by_count":1,"area":"mechinterp"},{"id":"2605.09224","title":"SMIXAE: Towards Unsupervised Manifold Discovery in Language Models","created":"2026-05-09","cited_by_count":1,"area":"mechinterp"},{"id":"2605.09967","title":"Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions","created":"2026-05-11","cited_by_count":1,"area":"mechinterp"},{"id":"2605.12770","title":"WriteSAE: Sparse Autoencoders for Recurrent State","created":"2026-05-12","cited_by_count":1,"area":"ssm"},{"id":"2605.25941","title":"Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models","created":"2026-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2605.27813","title":"Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models","created":"2026-05-27","cited_by_count":1,"area":"diffusion"},{"id":"2605.27819","title":"ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions","created":"2026-05-27","cited_by_count":1,"area":"mechinterp"},{"id":"2605.28870","title":"Representation Alignment Rests on Linear Structure","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.06857","title":"Interpreting Brain Responses to Language with Sparse Features from Language Models","created":"2026-06-05","cited_by_count":1,"area":"mechinterp"},{"id":"2606.07451","title":"TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment","created":"2026-06-05","cited_by_count":1,"area":"mllm"},{"id":"2606.10080","title":"VFUSE: Virulent Feature Understanding with Sparse autoEncoders","created":"2026-06-08","cited_by_count":1,"area":"mechinterp"},{"id":"2606.16193","title":"Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs","created":"2026-06-15","cited_by_count":1,"area":"mllm"},{"id":"2606.22994","title":"Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?","created":"2026-06-22","cited_by_count":1,"area":"mechinterp"},{"id":"2606.28548","title":"Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution","created":"2026-06-26","cited_by_count":1,"area":"mechinterp"},{"id":"2607.24645","title":"Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects","created":"2026-07-27","cited_by_count":1,"area":"mechinterp"},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.05575","title":"Capsule Lens: Locating and Tracking Concept Geometry in Model Representations","created":"2026-09-04","cited_by_count":1,"area":"mechinterp"},{"id":"2609.07037","title":"Disentangling Steering Vectors","created":"2026-09-07","cited_by_count":1,"area":"mechinterp"},{"id":"2505.22255","title":"Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders","created":"2025-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2507.10106","title":"BlueGlass: A Framework for Composite AI Safety","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2509.20784","title":"Towards Atoms of Large Language Models","created":"2025-09-25","cited_by_count":0,"area":"mechinterp"},{"id":"2509.22994","title":"Analysis of Variational Sparse Autoencoders","created":"2025-09-26","cited_by_count":0,"area":"mechinterp"},{"id":"2510.24672","title":"Eigenfunction Extraction for Ordered Representation Learning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2512.05794","title":"Mechanistic Interpretability of Antibody Language Models Using SAEs","created":"2025-12-05","cited_by_count":0,"area":"mechinterp"},{"id":"2512.19734","title":"The Deleuzian Representation Hypothesis","created":"2025-12-17","cited_by_count":0,"area":"mechinterp"},{"id":"2602.06806","title":"RAIGen: Rare Attribute Identification in Text-to-Image Generative Models","created":"2026-02-06","cited_by_count":0,"area":"diffusion"},{"id":"2603.13299","title":"DreamReader: An Interpretability Toolkit for Text-to-Image Models","created":"2026-03-02","cited_by_count":0,"area":"diffusion"},{"id":"2603.23794","title":"Sparse Autoencoders for Interpretable Medical Image Representation Learning","created":"2026-03-24","cited_by_count":0,"area":"mechinterp"}],"next_cursor":"100"}