{"total":131,"rows":[{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691,"area":null},{"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":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"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":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214,"area":null},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"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":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195,"area":null},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2403.00745","title":"AtP*: An efficient and scalable method for localizing LLM behaviour to components","created":"2024-03-01","cited_by_count":111,"area":"mechinterp"},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110,"area":"lr"},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2305.15054","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","created":"2023-05-24","cited_by_count":89,"area":"lr"},{"id":"2202.08816","title":"Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning","created":"2022-02-17","cited_by_count":79,"area":null},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"area":"lr"},{"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":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"area":null},{"id":"2207.14251","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","created":"2022-07-28","cited_by_count":57,"area":null},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"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":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47,"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":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2403.18167","title":"Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations","created":"2024-03-27","cited_by_count":38,"area":null},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34,"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":"2311.09433","title":"Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment","created":"2023-11-15","cited_by_count":30,"area":"safety"},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2203.09397","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","created":"2022-03-17","cited_by_count":28,"area":null},{"id":"2410.09223","title":"The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling","created":"2024-10-11","cited_by_count":28,"area":"mechinterp"},{"id":"2510.06182","title":"Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context","created":"2025-10-07","cited_by_count":26,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"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":"2410.06496","title":"On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task","created":"2024-10-09","cited_by_count":24,"area":null},{"id":"2303.07616","title":"The Life Cycle of Knowledge in Big Language Models: A Survey","created":"2023-03-14","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":"2305.14695","title":"A Causal View of Entity Bias in (Large) Language Models","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2505.16002","title":"Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions","created":"2025-05-21","cited_by_count":21,"area":null},{"id":"2205.07043","title":"Naturalistic Causal Probing for Morpho-Syntax","created":"2022-05-14","cited_by_count":19,"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":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2210.01963","title":"COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models","created":"2022-10-05","cited_by_count":15,"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":"2210.14328","title":"Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models","created":"2022-10-25","cited_by_count":14,"area":null},{"id":"2407.03779","title":"Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity","created":"2024-07-04","cited_by_count":14,"area":null},{"id":"2502.04577","title":"Position-aware Automatic Circuit Discovery","created":"2025-02-07","cited_by_count":14,"area":"mechinterp"},{"id":"2502.20344","title":"LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder","created":"2025-02-27","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":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2508.21258","title":"RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching","created":"2025-08-28","cited_by_count":13,"area":"mechinterp"},{"id":"2310.15151","title":"Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2311.08968","title":"Identifying Linear Relational Concepts in Large Language Models","created":"2023-11-15","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":"2211.03374","title":"Deep Causal Learning: Representation, Discovery and Inference","created":"2022-11-07","cited_by_count":11,"area":null},{"id":"2404.04332","title":"Scope Ambiguities in Large Language Models","created":"2024-04-05","cited_by_count":11,"area":null},{"id":"2410.22590","title":"Characterizing the Role of Similarity in the Property Inferences of Language Models","created":"2024-10-29","cited_by_count":11,"area":null},{"id":"2503.11302","title":"Are formal and functional linguistic mechanisms dissociated in language models?","created":"2025-03-14","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":"2510.04764","title":"Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models","created":"2025-10-06","cited_by_count":11,"area":null},{"id":"2602.08783","title":"Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2606.27510","title":"The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching","created":"2026-06-25","cited_by_count":11,"area":"mechinterp"},{"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":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2503.10894","title":"HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks","created":"2025-03-13","cited_by_count":9,"area":"mechinterp"},{"id":"2509.17196","title":"Evolution of Concepts in Language Model Pre-Training","created":"2025-09-21","cited_by_count":8,"area":null},{"id":"2212.04523","title":"Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement","created":"2022-12-08","cited_by_count":7,"area":null},{"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":"2502.13946","title":"Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region","created":"2025-02-19","cited_by_count":6,"area":"alignment"},{"id":"2505.22630","title":"Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs","created":"2025-05-28","cited_by_count":6,"area":null},{"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":"2604.12493","title":"Latent Planning Emerges with Scale","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2201.12911","title":"Grammatical cues to subjecthood are redundant in a majority of simple clauses across languages","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2307.03056","title":"Generalizing Backpropagation for Gradient-Based Interpretability","created":"2023-07-06","cited_by_count":5,"area":null},{"id":"2406.02335","title":"Probing the Category of Verbal Aspect in Transformer Language Models","created":"2024-06-04","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":"2504.15471","title":"Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models","created":"2025-04-21","cited_by_count":5,"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":"2503.11429","title":"Combining Causal Models for More Accurate Abstractions of Neural Networks","created":"2025-03-14","cited_by_count":4,"area":"mechinterp"},{"id":"2505.24244","title":"Mamba Knockout for Unraveling Factual Information Flow","created":"2025-05-30","cited_by_count":4,"area":"ssm"},{"id":"2508.12411","title":"The Cultural Gene of Large Language Models: A Study on the Impact of Cross-Corpus Training on Model Values and Biases","created":"2025-08-17","cited_by_count":4,"area":null},{"id":"2602.15183","title":"Seeing to Generalize: How Visual Data Corrects Binding Shortcuts","created":"2026-02-16","cited_by_count":4,"area":"mllm"},{"id":"2109.07542","title":"Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects","created":"2021-09-15","cited_by_count":3,"area":null},{"id":"2209.04761","title":"Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysis","created":"2022-09-11","cited_by_count":3,"area":null},{"id":"2305.08572","title":"Estimating the Causal Effects of Natural Logic Features in Neural NLI Models","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2502.06106","title":"Fine-Tuning is Subgraph Search: A New Lens on Learning Dynamics","created":"2025-02-10","cited_by_count":3,"area":"mechinterp"},{"id":"2510.23264","title":"PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization","created":"2025-10-27","cited_by_count":3,"area":"mechinterp"},{"id":"2602.22581","title":"IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck","created":"2026-02-26","cited_by_count":3,"area":"mechinterp"},{"id":"2604.00778","title":"From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks","created":"2026-04-01","cited_by_count":3,"area":"mechinterp"}],"next_cursor":"100"}