{"total":137,"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":"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":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312,"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":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196,"area":null},{"id":"2605.29358","title":"Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet","created":"2026-05-28","cited_by_count":191,"area":"mechinterp"},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147,"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":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108,"area":null},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91,"area":"mechinterp"},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2404.14394","title":"A Multimodal Automated Interpretability Agent","created":"2024-04-22","cited_by_count":63,"area":"agents"},{"id":"2302.14233","title":"Goal Driven Discovery of Distributional Differences via Language Descriptions","created":"2023-02-28","cited_by_count":62,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2305.13749","title":"Goal-Driven Explainable Clustering via Language Descriptions","created":"2023-05-23","cited_by_count":58,"area":null},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54,"area":null},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53,"area":null},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2308.01544","title":"Multimodal Neurons in Pretrained Text-Only Transformers","created":"2023-08-03","cited_by_count":49,"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":"2506.08010","title":"Vision Transformers Don't Need Trained Registers","created":"2025-06-09","cited_by_count":41,"area":null},{"id":"2311.07470","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","created":"2023-11-13","cited_by_count":36,"area":"mllm"},{"id":"2406.04341","title":"Interpreting the Second-Order Effects of Neurons in CLIP","created":"2024-06-06","cited_by_count":36,"area":null},{"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":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2307.10504","title":"Identifying Interpretable Subspaces in Image Representations","created":"2023-07-20","cited_by_count":32,"area":null},{"id":"2309.03886","title":"FIND: A Function Description Benchmark for Evaluating Interpretability Methods","created":"2023-09-07","cited_by_count":32,"area":null},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32,"area":null},{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2306.02879","title":"Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2406.11193","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","created":"2024-06-17","cited_by_count":26,"area":"mllm"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2502.06755","title":"Interpretable and Testable Vision Features via Sparse Autoencoders","created":"2025-02-10","cited_by_count":25,"area":"mechinterp"},{"id":"2503.24071","title":"From Colors to Classes: Emergence of Concepts in Vision Transformers","created":"2025-03-31","cited_by_count":23,"area":null},{"id":"2506.03292","title":"HyperSteer: Activation Steering at Scale with Hypernetworks","created":"2025-06-03","cited_by_count":23,"area":"mechinterp"},{"id":"2302.10894","title":"Red Teaming Deep Neural Networks with Feature Synthesis Tools","created":"2023-02-08","cited_by_count":21,"area":"safety"},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2405.06855","title":"Linear Explanations for Individual Neurons","created":"2024-05-10","cited_by_count":19,"area":null},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19,"area":"mechinterp"},{"id":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2410.04368","title":"Algorithmic Capabilities of Random Transformers","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2406.05191","title":"DiffusionPID: Interpreting Diffusion via Partial Information Decomposition","created":"2024-06-07","cited_by_count":16,"area":"diffusion"},{"id":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2402.18956","title":"WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts","created":"2024-02-29","cited_by_count":14,"area":null},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"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":"2404.14349","title":"Automatic Discovery of Visual Circuits","created":"2024-04-22","cited_by_count":13,"area":null},{"id":"2310.06200","title":"The Importance of Prompt Tuning for Automated Neuron Explanations","created":"2023-10-09","cited_by_count":12,"area":null},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2512.15712","title":"Predictive Concept Decoders: Training Scalable End-to-End Interpretability Assistants","created":"2025-12-17","cited_by_count":12,"area":null},{"id":"2310.07325","title":"An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L","created":"2023-10-11","cited_by_count":11,"area":null},{"id":"2310.10591","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations","created":"2023-10-16","cited_by_count":11,"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":"2306.08042","title":"FLamE: Few-shot Learning from Natural Language Explanations","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2309.01617","title":"DeViL: Decoding Vision features into Language","created":"2023-09-04","cited_by_count":10,"area":null},{"id":"2403.13771","title":"Interpreting Neurons in Deep Vision Networks with Language Models","created":"2024-03-20","cited_by_count":10,"area":null},{"id":"2503.10894","title":"HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks","created":"2025-03-13","cited_by_count":9,"area":"mechinterp"},{"id":"2503.21730","title":"Effective Skill Unlearning through Intervention and Abstention","created":"2025-03-27","cited_by_count":9,"area":"safety"},{"id":"2509.21972","title":"From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education","created":"2025-09-26","cited_by_count":9,"area":null},{"id":"2310.04929","title":"DISCOVER: Making Vision Networks Interpretable via Competition and Dissection","created":"2023-10-07","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":"2406.16990","title":"AND: Audio Network Dissection for Interpreting Deep Acoustic Models","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2407.12543","title":"Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2407.20899","title":"Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2503.09046","title":"Discovering Influential Neuron Path in Vision Transformers","created":"2025-03-12","cited_by_count":7,"area":null},{"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":"2406.08572","title":"LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2506.04706","title":"Line of Sight: On Linear Representations in VLLMs","created":"2025-06-05","cited_by_count":6,"area":"mechinterp"},{"id":"2206.13498","title":"Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2302.10291","title":"Can Large Language Models Change User Preference Adversarially?","created":"2023-01-05","cited_by_count":5,"area":"safety"},{"id":"2310.10708","title":"Automated Natural Language Explanation of Deep Visual Neurons with Large Models","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2401.10217","title":"Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions","created":"2024-01-18","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":"2508.01728","title":"Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations","created":"2025-08-03","cited_by_count":5,"area":"mechinterp"},{"id":"2512.07404","title":"On LLMs' Internal Representation of Code Correctness","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2512.08560","title":"BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain","created":"2025-12-09","cited_by_count":5,"area":null},{"id":"2203.01881","title":"Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features","created":"2022-03-03","cited_by_count":4,"area":null},{"id":"2308.06755","title":"Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining","created":"2023-08-13","cited_by_count":4,"area":null},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2405.01825","title":"Improving Concept Alignment in Vision-Language Concept Bottleneck Models","created":"2024-05-03","cited_by_count":4,"area":null},{"id":"2502.13606","title":"LaVCa: LLM-assisted Visual Cortex Captioning","created":"2025-02-19","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":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","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":"2409.15190","title":"Interpretability-Guided Test-Time Adversarial Defense","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2410.17832","title":"Exploiting Text-Image Latent Spaces for the Description of Visual Concepts","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2502.18485","title":"Deciphering Functions of Neurons in Vision-Language Models","created":"2025-02-10","cited_by_count":3,"area":"mllm"},{"id":"2304.13346","title":"Concept-Monitor: Understanding DNN training through individual neurons","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2310.16332","title":"Corrupting Neuron Explanations of Deep Visual Features","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2406.17241","title":"Understanding Language Model Circuits through Knowledge Editing","created":"2024-06-25","cited_by_count":2,"area":null}],"next_cursor":"100"}