{"total":876,"rows":[{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691,"area":null},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302,"area":null},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780,"area":null},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"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":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623,"area":"mechinterp"},{"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":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404,"area":null},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394,"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":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319,"area":"wm"},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"area":null},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259,"area":null},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246,"area":"lr"},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244,"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":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"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":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200,"area":null},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2504.05419","title":"Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification","created":"2025-04-07","cited_by_count":159,"area":"lr"},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"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":"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":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"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":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104,"area":null},{"id":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97,"area":"lr"},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91,"area":null},{"id":"2401.12973","title":"In-Context Language Learning: Architectures and Algorithms","created":"2024-01-23","cited_by_count":89,"area":null},{"id":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86,"area":null},{"id":"2407.03282","title":"LLM Internal States Reveal Hallucination Risk Faced With a Query","created":"2024-07-03","cited_by_count":82,"area":null},{"id":"2406.12775","title":"Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries","created":"2024-06-18","cited_by_count":78,"area":null},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77,"area":"mechinterp"},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2402.16061","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","created":"2024-02-25","cited_by_count":64,"area":null},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2312.03729","title":"Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?","created":"2023-11-27","cited_by_count":62,"area":null},{"id":"2403.15498","title":"Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models","created":"2024-03-21","cited_by_count":62,"area":"wm"},{"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":"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":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"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":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2404.00859","title":"Do language models plan ahead for future tokens?","created":"2024-04-01","cited_by_count":49,"area":null},{"id":"2507.06952","title":"What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models","created":"2025-07-09","cited_by_count":47,"area":"wm"},{"id":"2402.12560","title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","created":"2024-02-19","cited_by_count":46,"area":null},{"id":"2406.07882","title":"Designing a Dashboard for Transparency and Control of Conversational AI","created":"2024-06-12","cited_by_count":46,"area":null},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41,"area":null},{"id":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41,"area":null},{"id":"2306.01128","title":"Learning Transformer Programs","created":"2023-06-01","cited_by_count":41,"area":"mechinterp"},{"id":"2401.06751","title":"The Unreasonable Effectiveness of Easy Training Data for Hard Tasks","created":"2024-01-12","cited_by_count":40,"area":"lr"},{"id":"2303.09859","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","created":"2023-03-17","cited_by_count":39,"area":null},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2404.03646","title":"Locating and Editing Factual Associations in Mamba","created":"2024-04-04","cited_by_count":37,"area":"ssm"},{"id":"2410.06331","title":"Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing","created":"2024-10-08","cited_by_count":37,"area":null},{"id":"2412.12444","title":"LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers","created":"2024-12-17","cited_by_count":37,"area":"diffusion"},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2206.02608","title":"What do tokens know about their characters and how do they know it?","created":"2022-06-06","cited_by_count":36,"area":null},{"id":"2306.06232","title":"Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration","created":"2023-06-09","cited_by_count":36,"area":null},{"id":"2506.09278","title":"UFM: A Simple Path towards Unified Dense Correspondence with Flow","created":"2025-06-10","cited_by_count":36,"area":null},{"id":"2410.01035","title":"Don't Stop Me Now: Embedding Based Scheduling for LLMs","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2502.11356","title":"SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models","created":"2025-02-17","cited_by_count":34,"area":"mechinterp"},{"id":"2410.11781","title":"Language Models Encode Numbers Using Digit Representations in Base 10","created":"2024-10-15","cited_by_count":32,"area":null},{"id":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32,"area":"mechinterp"},{"id":"2503.02080","title":"Linear Representations of Political Perspective Emerge in Large Language Models","created":"2025-03-03","cited_by_count":32,"area":"mechinterp"},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2203.14139","title":"Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages","created":"2022-03-26","cited_by_count":30,"area":null},{"id":"2305.11169","title":"Emergent Representations of Program Semantics in Language Models Trained on Programs","created":"2023-05-18","cited_by_count":30,"area":"wm"},{"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":"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":"2403.05846","title":"Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines","created":"2024-03-09","cited_by_count":30,"area":"diffusion"},{"id":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30,"area":"mllm"},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2306.02295","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","created":"2023-06-04","cited_by_count":29,"area":null},{"id":"2411.03343","title":"What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks","created":"2024-11-02","cited_by_count":29,"area":"safety"},{"id":"2505.16188","title":"SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models","created":"2025-05-22","cited_by_count":29,"area":"mechinterp"},{"id":"2511.00617","title":"Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering","created":"2025-11-01","cited_by_count":29,"area":"mechinterp"},{"id":"2401.13544","title":"Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2406.01394","title":"PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration","created":"2024-06-03","cited_by_count":28,"area":null},{"id":"2410.24159","title":"GPT or BERT: why not both?","created":"2024-10-31","cited_by_count":27,"area":null},{"id":"2502.05489","title":"Mechanistic Interpretability of Emotion Inference in Large Language Models","created":"2025-02-08","cited_by_count":27,"area":"mechinterp"}],"next_cursor":"100"}