{"total":103,"rows":[{"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":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267,"area":null},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149,"area":null},{"id":"2402.14811","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","created":"2024-02-22","cited_by_count":149,"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":"2307.16376","title":"When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities","created":"2023-07-31","cited_by_count":90,"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":"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":"2312.09230","title":"Successor Heads: Recurring, Interpretable Attention Heads In The Wild","created":"2023-12-14","cited_by_count":77,"area":null},{"id":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62,"area":"mechinterp"},{"id":"2406.16778","title":"Finding Transformer Circuits with Edge Pruning","created":"2024-06-24","cited_by_count":60,"area":null},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2402.18312","title":"How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning","created":"2024-02-28","cited_by_count":53,"area":"lr"},{"id":"2310.14491","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","created":"2023-10-23","cited_by_count":50,"area":"lr"},{"id":"2405.02421","title":"What does the Knowledge Neuron Thesis Have to do with Knowledge?","created":"2024-05-03","cited_by_count":49,"area":null},{"id":"2402.12560","title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","created":"2024-02-19","cited_by_count":46,"area":null},{"id":"2407.14561","title":"NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals","created":"2024-07-18","cited_by_count":45,"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":"2306.08666","title":"Radiology-GPT: A Large Language Model for Radiology","created":"2023-06-14","cited_by_count":44,"area":null},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","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":"2404.03502","title":"AI and the Problem of Knowledge Collapse","created":"2024-04-04","cited_by_count":34,"area":null},{"id":"2403.09606","title":"Large Language Models and Causal Inference in Collaboration: A Survey","created":"2024-03-14","cited_by_count":26,"area":null},{"id":"2407.14494","title":"InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques","created":"2024-07-19","cited_by_count":25,"area":"mechinterp"},{"id":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","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":"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":"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":"2407.04690","title":"Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks","created":"2024-07-05","cited_by_count":23,"area":null},{"id":"2407.15248","title":"XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models","created":"2024-07-21","cited_by_count":23,"area":null},{"id":"2402.03268","title":"Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation","created":"2024-02-05","cited_by_count":22,"area":"lr"},{"id":"2502.06852","title":"EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification","created":"2025-02-07","cited_by_count":21,"area":"mechinterp"},{"id":"2312.10091","title":"Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models","created":"2023-12-13","cited_by_count":18,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2401.12631","title":"A Reply to Makelov et al. (2023)'s \"Interpretability Illusion\" Arguments","created":"2024-01-23","cited_by_count":17,"area":null},{"id":"2406.18400","title":"Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers","created":"2024-06-26","cited_by_count":15,"area":null},{"id":"2506.05166","title":"Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective","created":"2025-06-05","cited_by_count":15,"area":"mechinterp"},{"id":"2406.15955","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","created":"2024-06-22","cited_by_count":13,"area":null},{"id":"2311.04354","title":"Uncovering Intermediate Variables in Transformers using Circuit Probing","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2401.04854","title":"Are Language Models More Like Libraries or Like Librarians? Bibliotechnism, the Novel Reference Problem, and the Attitudes of LLMs","created":"2024-01-10","cited_by_count":11,"area":null},{"id":"2403.11894","title":"From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?","created":"2024-03-18","cited_by_count":11,"area":null},{"id":"2406.00394","title":"Learning Causal Abstractions of Linear Structural Causal Models","created":"2024-06-01","cited_by_count":11,"area":null},{"id":"2409.09825","title":"GP-GPT: Large Language Model for Gene-Phenotype Mapping","created":"2024-09-15","cited_by_count":11,"area":null},{"id":"2410.15580","title":"Language Models are Symbolic Learners in Arithmetic","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2505.11770","title":"Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2602.16823","title":"Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees","created":"2026-02-18","cited_by_count":11,"area":"mechinterp"},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","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":"2505.05145","title":"Understanding In-context Learning of Addition via Activation Subspaces","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2508.01916","title":"Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning","created":"2025-08-03","cited_by_count":8,"area":"mechinterp"},{"id":"2306.03882","title":"Causal interventions expose implicit situation models for commonsense language understanding","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2405.17653","title":"InversionView: A General-Purpose Method for Reading Information from Neural Activations","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2406.18534","title":"Towards Compositionality in Concept Learning","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2511.04638","title":"Addressing divergent representations from causal interventions on neural networks","created":"2025-11-06","cited_by_count":7,"area":"mechinterp"},{"id":"2501.06141","title":"Emergent Symbol-like Number Variables in Artificial Neural Networks","created":"2025-01-10","cited_by_count":6,"area":null},{"id":"2406.09464","title":"GPT-ology, Computational Models, Silicon Sampling: How should we think about LLMs in Cognitive Science?","created":"2024-06-13","cited_by_count":5,"area":"lr"},{"id":"2504.06303","title":"On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions","created":"2025-04-07","cited_by_count":5,"area":null},{"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":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2512.16902","title":"In-Context Algebra","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2407.13594","title":"Validating Mechanistic Interpretations: An Axiomatic Approach","created":"2024-07-18","cited_by_count":4,"area":"mechinterp"},{"id":"2503.11429","title":"Combining Causal Models for More Accurate Abstractions of Neural Networks","created":"2025-03-14","cited_by_count":4,"area":"mechinterp"},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2602.08159","title":"The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models","created":"2026-02-08","cited_by_count":4,"area":"mechinterp"},{"id":"2607.08349","title":"Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability","created":"2026-07-09","cited_by_count":4,"area":"mechinterp"},{"id":"2501.06164","title":"Model Alignment Search","created":"2025-01-10","cited_by_count":3,"area":"alignment"},{"id":"2503.16401","title":"Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them","created":"2025-03-20","cited_by_count":3,"area":"lr"},{"id":"2506.16975","title":"Latent Concept Disentanglement in Transformer-based Language Models","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2602.22581","title":"IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck","created":"2026-02-26","cited_by_count":3,"area":"mechinterp"},{"id":"2606.09899","title":"When Attribution Patching Lies: Diagnosis and a Second-Order Correction","created":"2026-06-05","cited_by_count":3,"area":"mechinterp"},{"id":"2410.20161","title":"Causal Abstraction in Model Interpretability: A Compact Survey","created":"2024-10-26","cited_by_count":2,"area":null},{"id":"2507.05387","title":"The Generalization Ridge: Information Flow in Natural Language Generation","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2601.10700","title":"LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2606.32022","title":"SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2405.07436","title":"Can Language Models Explain Their Own Classification Behavior?","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2503.16724","title":"Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models","created":"2025-03-20","cited_by_count":1,"area":"mllm"},{"id":"2508.15875","title":"NEAT: Concept driven Neuron Attribution in LLMs","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2603.13201","title":"Neuron-Aware Data Selection In Instruction Tuning For Large Language Models","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2605.02234","title":"Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.08012","title":"Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.16023","title":"Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.19594","title":"Unsupervised Causal Abstractions Discovery","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2311.10905","title":"Flexible Model Interpretability through Natural Language Model Editing","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2502.12013","title":"Unsupervised Structural-Counterfactual Generation under Domain Shift","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2603.10377","title":"Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2605.06979","title":"PLOT: Progressive Localization via Optimal Transport in Neural Causal Abstraction","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.19135","title":"Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.11945","title":"Belief-reality separation lives in routing over a shared value slot in language models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.28672","title":"LAWFUL: Law-Aligned Witness for Faithful Use of Latents","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.10172","title":"Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability","created":"2026-08-10","cited_by_count":0,"area":"mechinterp"},{"id":"2609.08879","title":"Medical AI Encodes a \"Feeling of Error\": Verifying Cancer Segmentation via Internal Concepts","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.32907","title":"Logical subspace in LLMs","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37680","title":"When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"}],"next_cursor":"100"}