{"total":165,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319,"area":"wm"},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159,"area":null},{"id":"2410.20526","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","created":"2024-10-27","cited_by_count":143,"area":"mechinterp"},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122,"area":null},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119,"area":null},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115,"area":"mechinterp"},{"id":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113,"area":"mechinterp"},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108,"area":null},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2411.02193","title":"Improving Steering Vectors by Targeting Sparse Autoencoder Features","created":"2024-11-04","cited_by_count":92,"area":"mechinterp"},{"id":"2405.08366","title":"Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control","created":"2024-05-14","cited_by_count":86,"area":"mechinterp"},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2311.17030","title":"Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching","created":"2023-11-28","cited_by_count":80,"area":"mechinterp"},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2405.12241","title":"Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning","created":"2024-05-17","cited_by_count":67,"area":"mechinterp"},{"id":"2412.12101","title":"InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders","created":"2024-11-13","cited_by_count":66,"area":"mechinterp"},{"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":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"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":"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":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2310.06714","title":"Exploring Memorization in Fine-tuned Language Models","created":"2023-10-10","cited_by_count":45,"area":null},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39,"area":null},{"id":"2406.03662","title":"The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision","created":"2024-06-06","cited_by_count":37,"area":"mechinterp"},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2408.05451","title":"Mathematical Models of Computation in Superposition","created":"2024-08-10","cited_by_count":35,"area":"mechinterp"},{"id":"2305.15614","title":"Reverse Engineering Self-Supervised Learning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2505.10465","title":"Superposition Yields Robust Neural Scaling","created":"2025-05-15","cited_by_count":31,"area":"mechinterp"},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2305.16536","title":"Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression","created":"2023-05-25","cited_by_count":30,"area":null},{"id":"2503.10996","title":"Taming Knowledge Conflicts in Language Models","created":"2025-03-14","cited_by_count":30,"area":null},{"id":"2605.26379","title":"When Does LeJEPA Learn a World Model?","created":"2026-05-25","cited_by_count":30,"area":"wm"},{"id":"2402.12201","title":"Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT","created":"2024-02-19","cited_by_count":29,"area":"mechinterp"},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2410.07656","title":"Mechanistic Permutability: Match Features Across Layers","created":"2024-10-10","cited_by_count":22,"area":"mechinterp"},{"id":"2409.15318","title":"On the Complexity of Neural Computation in Superposition","created":"2024-09-05","cited_by_count":21,"area":"mechinterp"},{"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":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2502.08009","title":"The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2301.00709","title":"Tsetlin Machine Embedding: Representing Words Using Logical Expressions","created":"2023-01-02","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2104.08809","title":"SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts","created":"2021-04-18","cited_by_count":14,"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":"2410.21331","title":"Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2412.04139","title":"Monet: Mixture of Monosemantic Experts for Transformers","created":"2024-12-05","cited_by_count":13,"area":"mechinterp"},{"id":"2501.08145","title":"Refusal Behavior in Large Language Models: A Nonlinear Perspective","created":"2025-01-14","cited_by_count":13,"area":null},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2105.10360","title":"Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices","created":"2021-05-21","cited_by_count":10,"area":null},{"id":"2502.00620","title":"Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions","created":"2025-02-02","cited_by_count":10,"area":null},{"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":"2406.11624","title":"Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2504.20938","title":"Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition","created":"2025-04-29","cited_by_count":9,"area":"mechinterp"},{"id":"2510.00404","title":"AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2106.08495","title":"Improving Entity Linking through Semantic Reinforced Entity Embeddings","created":"2021-06-16","cited_by_count":8,"area":null},{"id":"2106.14365","title":"Integrating topic modeling and word embedding to characterize violent deaths","created":"2021-06-28","cited_by_count":8,"area":null},{"id":"2211.13095","title":"Schr\\\"{o}dinger's Bat: Diffusion Models Sometimes Generate Polysemous Words in Superposition","created":"2022-11-23","cited_by_count":8,"area":"diffusion"},{"id":"2104.07198","title":"Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2405.15756","title":"Wasserstein Distances, Neuronal Entanglement, and Sparsity","created":"2024-05-24","cited_by_count":6,"area":"mechinterp"},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2508.16929","title":"Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning","created":"2025-08-23","cited_by_count":6,"area":"mechinterp"},{"id":"2511.19265","title":"Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks","created":"2025-11-24","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":"2101.10448","title":"PolyLM: Learning about Polysemy through Language Modeling","created":"2021-01-25","cited_by_count":5,"area":null},{"id":"2107.10413","title":"Theoretical foundations and limits of word embeddings: what types of meaning can they capture?","created":"2021-07-22","cited_by_count":5,"area":null},{"id":"2112.08491","title":"Human Languages with Greater Information Density Increase Communication Speed, but Decrease Conversation Breadth","created":"2021-12-15","cited_by_count":5,"area":null},{"id":"2312.15611","title":"Inference of Dependency Knowledge Graph for Electronic Health Records","created":"2023-12-25","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":"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":"2506.03790","title":"Attention-Only Transformers via Unrolled Subspace Denoising","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2606.25008","title":"Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2105.08585","title":"Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings","created":"2021-05-18","cited_by_count":4,"area":null},{"id":"2505.08080","title":"Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders","created":"2025-05-12","cited_by_count":4,"area":"mechinterp"},{"id":"2505.15811","title":"On the creation of narrow AI: hierarchy and nonlocality of neural network skills","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2508.17320","title":"AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations","created":"2025-08-24","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":"2103.15330","title":"Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2310.07837","title":"Measuring Feature Sparsity in Language Models","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2403.14926","title":"Contrastive Learning on Multimodal Analysis of Electronic Health Records","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2410.24184","title":"Group Crosscoders for Mechanistic Analysis of Symmetry","created":"2024-10-31","cited_by_count":3,"area":"mechinterp"},{"id":"2503.02078","title":"Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation","created":"2025-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2509.25596","title":"Binary Sparse Coding for Interpretability","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"}],"next_cursor":"100"}