{"total":129,"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":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"area":"mechinterp"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359,"area":"mechinterp"},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"area":null},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235,"area":"mechinterp"},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108,"area":null},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104,"area":null},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96,"area":null},{"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":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"area":null},{"id":"2310.10616","title":"How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations","created":"2023-10-16","cited_by_count":75,"area":null},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2404.00806","title":"Algorithmic Collusion by Large Language Models","created":"2024-03-31","cited_by_count":62,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"id":"2402.14328","title":"Understanding and Patching Compositional Reasoning in LLMs","created":"2024-02-22","cited_by_count":46,"area":"lr"},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2404.08978","title":"Incremental Residual Concept Bottleneck Models","created":"2024-04-13","cited_by_count":43,"area":null},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2307.03637","title":"Discovering Variable Binding Circuitry with Desiderata","created":"2023-07-07","cited_by_count":34,"area":null},{"id":"2310.13121","title":"Understanding Addition in Transformers","created":"2023-10-19","cited_by_count":34,"area":null},{"id":"2309.10498","title":"A Configurable Library for Generating and Manipulating Maze Datasets","created":"2023-09-19","cited_by_count":31,"area":null},{"id":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2302.12461","title":"Analyzing And Editing Inner Mechanisms Of Backdoored Language Models","created":"2023-02-24","cited_by_count":23,"area":"safety"},{"id":"2312.08550","title":"Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2407.00886","title":"Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition","created":"2024-07-01","cited_by_count":23,"area":"mechinterp"},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2302.10894","title":"Red Teaming Deep Neural Networks with Feature Synthesis Tools","created":"2023-02-08","cited_by_count":21,"area":"safety"},{"id":"2406.11779","title":"Compact Proofs of Model Performance via Mechanistic Interpretability","created":"2024-06-17","cited_by_count":18,"area":"mechinterp"},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"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":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"area":null},{"id":"2310.04475","title":"Demystifying Embedding Spaces using Large Language Models","created":"2023-10-06","cited_by_count":17,"area":null},{"id":"2401.17975","title":"Understanding polysemanticity in neural networks through coding theory","created":"2024-01-31","cited_by_count":17,"area":null},{"id":"2312.02566","title":"Structured World Representations in Maze-Solving Transformers","created":"2023-12-05","cited_by_count":16,"area":null},{"id":"2502.11019","title":"Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2405.12522","title":"Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models","created":"2024-05-21","cited_by_count":15,"area":"mechinterp"},{"id":"2406.00053","title":"Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting","created":"2024-05-28","cited_by_count":15,"area":null},{"id":"2411.06090","title":"Concept Bottleneck Language Models For protein design","created":"2024-11-09","cited_by_count":15,"area":null},{"id":"2510.00845","title":"Mechanistic Interpretability as Statistical Estimation: A Variance Analysis","created":"2025-10-01","cited_by_count":15,"area":"mechinterp"},{"id":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2404.18191","title":"Exploring the Robustness of In-Context Learning with Noisy Labels","created":"2024-04-28","cited_by_count":14,"area":null},{"id":"2310.11884","title":"From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2405.10927","title":"Using Degeneracy in the Loss Landscape for Mechanistic Interpretability","created":"2024-05-17","cited_by_count":13,"area":"mechinterp"},{"id":"2412.11867","title":"Transformers Use Causal World Models in Maze-Solving Tasks","created":"2024-12-16","cited_by_count":13,"area":"wm"},{"id":"2308.01154","title":"Arithmetic with Language Models: from Memorization to Computation","created":"2023-08-02","cited_by_count":12,"area":null},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2505.24650","title":"Beyond the Black Box: Interpretability of LLMs in Finance","created":"2025-05-14","cited_by_count":11,"area":"mechinterp"},{"id":"2602.16823","title":"Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees","created":"2026-02-18","cited_by_count":11,"area":"mechinterp"},{"id":"2410.07476","title":"Towards a unified and verified understanding of group-operation networks","created":"2024-10-09","cited_by_count":10,"area":"mechinterp"},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2311.13186","title":"Applications of Spiking Neural Networks in Visual Place Recognition","created":"2023-11-22","cited_by_count":9,"area":null},{"id":"2509.17588","title":"Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models","created":"2025-09-22","cited_by_count":9,"area":"mllm"},{"id":"2306.02149","title":"A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functions","created":"2023-06-03","cited_by_count":8,"area":null},{"id":"2306.07397","title":"Adversarial Attacks on the Interpretation of Neuron Activation Maximization","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2405.17088","title":"Phase Transitions in the Output Distribution of Large Language Models","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2410.03020","title":"On Logical Extrapolation for Mazes with Recurrent and Implicit Networks","created":"2024-10-03","cited_by_count":7,"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":"2211.10024","title":"Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2506.02996","title":"Linear Spatial World Models Emerge in Large Language Models","created":"2025-06-03","cited_by_count":6,"area":"wm"},{"id":"2506.18852","title":"Mechanistic Interpretability Needs Philosophy","created":"2025-06-23","cited_by_count":6,"area":"mechinterp"},{"id":"2302.10291","title":"Can Large Language Models Change User Preference Adversarially?","created":"2023-01-05","cited_by_count":5,"area":"safety"},{"id":"2408.12664","title":"Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2409.13684","title":"The FIX Benchmark: Extracting Features Interpretable to eXperts","created":"2024-09-20","cited_by_count":5,"area":null},{"id":"2411.02461","title":"Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2505.16705","title":"An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2402.03855","title":"Challenges in Mechanistically Interpreting Model Representations","created":"2024-02-06","cited_by_count":4,"area":"mechinterp"},{"id":"2404.08964","title":"Understanding Multimodal Deep Neural Networks: A Concept Selection View","created":"2024-04-13","cited_by_count":4,"area":null},{"id":"2404.18988","title":"Markovian Transformers for Informative Language Modeling","created":"2024-04-29","cited_by_count":4,"area":"lr"},{"id":"2407.13594","title":"Validating Mechanistic Interpretations: An Axiomatic Approach","created":"2024-07-18","cited_by_count":4,"area":"mechinterp"},{"id":"2605.05076","title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2309.10209","title":"Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspective","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2312.05361","title":"Emergence and Function of Abstract Representations in Self-Supervised Transformers","created":"2023-12-08","cited_by_count":3,"area":"wm"},{"id":"2402.08211","title":"Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2404.02949","title":"The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2407.10543","title":"Understanding the Dependence of Perception Model Competency on Regions in an Image","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2410.11468","title":"Can sparse autoencoders make sense of gene expression latent variable models?","created":"2024-10-15","cited_by_count":3,"area":"mechinterp"},{"id":"2501.18887","title":"Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability","created":"2025-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2505.13899","title":"Causes and Consequences of Representational Similarity in Machine Learning Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2607.22367","title":"Interior interpretability with attention rollout: contraction and propagation profiles in Transformers","created":"2026-07-24","cited_by_count":3,"area":null},{"id":"2302.09071","title":"Rejecting Cognitivism: Computational Phenomenology for Deep Learning","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2303.01739","title":"Study of Distractors in Neural Models of Code","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2303.15201","title":"Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Following","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2306.12609","title":"Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2406.02060","title":"I've got the \"Answer\"! Interpretation of LLMs Hidden States in Question Answering","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2410.18541","title":"On Explaining with Attention Matrices","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2507.00163","title":"Prompting as Scientific Inquiry","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2604.13694","title":"Weight Patching: Toward Source-Level Mechanistic Localization in LLMs","created":"2026-04-15","cited_by_count":2,"area":"mechinterp"}],"next_cursor":"100"}