{"total":97,"rows":[{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165,"area":"mechinterp"},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"area":"mechinterp"},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553,"area":"mechinterp"},{"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":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200,"area":"mechinterp"},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195,"area":null},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179,"area":"mechinterp"},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115,"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":"2401.12973","title":"In-Context Language Learning: Architectures and Algorithms","created":"2024-01-23","cited_by_count":89,"area":null},{"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":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"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":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"area":null},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2501.06346","title":"Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages","created":"2025-01-10","cited_by_count":59,"area":null},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46,"area":null},{"id":"2409.01659","title":"Interpreting and Improving Large Language Models in Arithmetic Calculation","created":"2024-09-03","cited_by_count":45,"area":null},{"id":"2511.13653","title":"Weight-sparse transformers have interpretable circuits","created":"2025-11-17","cited_by_count":44,"area":"mechinterp"},{"id":"2306.01128","title":"Learning Transformer Programs","created":"2023-06-01","cited_by_count":41,"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":"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":"2409.04478","title":"Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small","created":"2024-09-05","cited_by_count":34,"area":"mechinterp"},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33,"area":"mechinterp"},{"id":"2406.02128","title":"Iteration Head: A Mechanistic Study of Chain-of-Thought","created":"2024-06-04","cited_by_count":31,"area":"lr"},{"id":"2312.01429","title":"Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars","created":"2023-12-03","cited_by_count":30,"area":null},{"id":"2402.12550","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","created":"2024-02-19","cited_by_count":28,"area":"moe"},{"id":"2305.19911","title":"Neuron to Graph: Interpreting Language Model Neurons at Scale","created":"2023-05-31","cited_by_count":27,"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":"2312.03656","title":"Interpretability Illusions in the Generalization of Simplified Models","created":"2023-12-06","cited_by_count":25,"area":null},{"id":"2410.03334","title":"An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation","created":"2024-10-04","cited_by_count":25,"area":"mechinterp"},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2312.06581","title":"Grokking Group Multiplication with Cosets","created":"2023-12-11","cited_by_count":24,"area":null},{"id":"2405.05847","title":"Learned feature representations are biased by complexity, learning order, position, and more","created":"2024-05-09","cited_by_count":23,"area":null},{"id":"2502.11367","title":"Sparse Autoencoder Features for Classifications and Transferability","created":"2025-02-17","cited_by_count":21,"area":"mechinterp"},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2410.01537","title":"Attention layers provably solve single-location regression","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2412.11965","title":"Inferring Functionality of Attention Heads from their Parameters","created":"2024-12-16","cited_by_count":17,"area":null},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2406.10868","title":"Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts","created":"2024-06-16","cited_by_count":14,"area":null},{"id":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2402.15055","title":"Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions","created":"2024-02-23","cited_by_count":12,"area":null},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2601.20834","title":"Linear representations in language models can change dramatically over a conversation","created":"2026-01-28","cited_by_count":10,"area":null},{"id":"2312.04712","title":"Error Discovery by Clustering Influence Embeddings","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2205.09067","title":"Automatic Rule Induction for Interpretable Semi-Supervised Learning","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2212.11415","title":"Circumventing interpretability: How to defeat mind-readers","created":"2022-12-21","cited_by_count":6,"area":null},{"id":"2501.09653","title":"The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2503.06202","title":"Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2402.01702","title":"Fluent dreaming for language models","created":"2024-01-24","cited_by_count":5,"area":null},{"id":"2506.10920","title":"Constructing Interpretable Features from Compositional Neuron Groups","created":"2025-06-12","cited_by_count":5,"area":"mechinterp"},{"id":"2507.01936","title":"The Thin Line Between Comprehension and Persuasion in LLMs","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2304.12918","title":"N2G: A Scalable Approach for Quantifying Interpretable Neuron Representations in Large Language Models","created":"2023-04-22","cited_by_count":4,"area":"mechinterp"},{"id":"2410.06024","title":"Jet Expansions of Residual Computation","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2412.05353","title":"Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models","created":"2024-12-06","cited_by_count":4,"area":null},{"id":"2506.05774","title":"Evaluating Neuron Explanations: A Unified Framework with Sanity Checks","created":"2025-06-06","cited_by_count":4,"area":"mechinterp"},{"id":"2509.17665","title":"Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models","created":"2025-09-22","cited_by_count":4,"area":"mechinterp"},{"id":"2302.09304","title":"Interpretability in Activation Space Analysis of Transformers: A Focused Survey","created":"2023-01-22","cited_by_count":3,"area":"mechinterp"},{"id":"2311.08240","title":"Investigating the Encoding of Words in BERT's Neurons using Feature Textualization","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2502.11806","title":"Exploring the Translation Mechanism of Large Language Models","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2504.07831","title":"Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems","created":"2025-04-10","cited_by_count":3,"area":"mechinterp"},{"id":"2510.01048","title":"Interpreting Language Models Through Concept Descriptions: A Survey","created":"2025-10-01","cited_by_count":3,"area":"mechinterp"},{"id":"2604.06005","title":"Disentangling MLP Neuron Weights in Vocabulary Space","created":"2026-04-07","cited_by_count":3,"area":"mechinterp"},{"id":"2605.31183","title":"Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines","created":"2026-05-29","cited_by_count":3,"area":"mechinterp"},{"id":"2606.06267","title":"Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery","created":"2026-06-04","cited_by_count":3,"area":"mechinterp"},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2208.11450","title":"VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition","created":"2022-08-24","cited_by_count":2,"area":null},{"id":"2305.14728","title":"SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2411.08166","title":"Tackling Polysemanticity with Neuron Embeddings","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2507.12202","title":"Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control","created":"2025-07-16","cited_by_count":2,"area":"mechinterp"},{"id":"2607.13075","title":"The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators","created":"2026-07-12","cited_by_count":2,"area":"safety"},{"id":"2110.00125","title":"Combining Transformers with Natural Language Explanations","created":"2021-09-02","cited_by_count":1,"area":null},{"id":"2604.07615","title":"ADAG: Automatically Describing Attribution Graphs","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2510.03315","title":"Decomposing Attention To Find Context-Sensitive Neurons","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.11390","title":"Medical Interpretability and Knowledge Maps of Large Language Models","created":"2025-10-13","cited_by_count":0,"area":"mechinterp"},{"id":"2605.16468","title":"Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.28149","title":"Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations","created":"2026-05-27","cited_by_count":0,"area":"mechinterp"},{"id":"2608.13337","title":"Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation","created":"2026-08-13","cited_by_count":0,"area":"mechinterp"},{"id":"2608.24901","title":"Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.04808","title":"Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3","created":"2026-09-04","cited_by_count":0,"area":"mechinterp"},{"id":"2609.10792","title":"Analyzing Traditional and Neural Approaches to Multilingual Readability Assessment","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.14754","title":"Calibrating Interpretability Instruments Before Trusting Their Verdicts","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.02173","title":"Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}