{"total":195,"rows":[{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"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":"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":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"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":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218,"area":"mechinterp"},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214,"area":null},{"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":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200,"area":"mechinterp"},{"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":"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":"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":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108,"area":"mechinterp"},{"id":"2402.18154","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","created":"2024-02-28","cited_by_count":91,"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":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"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":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"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":"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":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"id":"2406.16778","title":"Finding Transformer Circuits with Edge Pruning","created":"2024-06-24","cited_by_count":60,"area":null},{"id":"2403.07809","title":"pyvene: A Library for Understanding and Improving PyTorch Models via Interventions","created":"2024-03-12","cited_by_count":54,"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":"2402.12560","title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","created":"2024-02-19","cited_by_count":46,"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":"2406.17759","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","created":"2024-06-25","cited_by_count":43,"area":"mechinterp"},{"id":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"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":"2312.12141","title":"Neuron-Level Knowledge Attribution in Large Language Models","created":"2023-12-19","cited_by_count":37,"area":null},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2410.12949","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","created":"2024-10-16","cited_by_count":35,"area":"safety"},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29,"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":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2407.17686","title":"Transformers on Markov Data: Constant Depth Suffices","created":"2024-07-25","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":"2312.03656","title":"Interpretability Illusions in the Generalization of Simplified Models","created":"2023-12-06","cited_by_count":25,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","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":"2407.00886","title":"Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition","created":"2024-07-01","cited_by_count":23,"area":"mechinterp"},{"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":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2407.08734","title":"Transformer Circuit Faithfulness Metrics are not Robust","created":"2024-07-11","cited_by_count":22,"area":"mechinterp"},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"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":"2507.22928","title":"How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding","created":"2025-07-24","cited_by_count":19,"area":"lr"},{"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":"2310.03084","title":"Discovering Knowledge-Critical Subnetworks in Pretrained Language Models","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2311.04131","title":"Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models","created":"2023-11-07","cited_by_count":15,"area":"mechinterp"},{"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":"2405.15302","title":"Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism","created":"2024-05-24","cited_by_count":15,"area":"lr"},{"id":"2506.05166","title":"Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective","created":"2025-06-05","cited_by_count":15,"area":"mechinterp"},{"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":"2404.14349","title":"Automatic Discovery of Visual Circuits","created":"2024-04-22","cited_by_count":13,"area":null},{"id":"2508.15882","title":"Beyond Transcription: Mechanistic Interpretability in ASR","created":"2025-08-21","cited_by_count":13,"area":"mechinterp"},{"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":"2310.07325","title":"An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L","created":"2023-10-11","cited_by_count":11,"area":null},{"id":"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":"2505.10039","title":"Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates","created":"2025-05-15","cited_by_count":10,"area":"lr"},{"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":"2603.24543","title":"Analysing the Safety Pitfalls of Steering Vectors","created":"2026-03-25","cited_by_count":10,"area":"safety"},{"id":"2502.10927","title":"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training","created":"2025-02-15","cited_by_count":9,"area":null},{"id":"2405.10928","title":"The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks","created":"2024-05-17","cited_by_count":8,"area":"mechinterp"},{"id":"2502.15801","title":"An explainable transformer circuit for compositional generalization","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2505.23701","title":"Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2602.11180","title":"Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions","created":"2026-01-21","cited_by_count":8,"area":"alignment"},{"id":"2602.20330","title":"Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking","created":"2026-02-23","cited_by_count":8,"area":"lr"},{"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":"2411.12118","title":"Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers","created":"2024-11-18","cited_by_count":7,"area":null},{"id":"2605.13156","title":"Dual-Pathway Circuits of Object Hallucination in Vision-Language Models","created":"2026-05-13","cited_by_count":7,"area":"lr"},{"id":"2406.13131","title":"When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2502.04645","title":"Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25","created":"2025-02-07","cited_by_count":6,"area":null},{"id":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2506.18141","title":"Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models","created":"2025-06-22","cited_by_count":6,"area":"mechinterp"},{"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":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2606.00831","title":"Subliminal Learning is a LoRA Artifact","created":"2026-05-30","cited_by_count":6,"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":"2504.13756","title":"Scaling sparse feature circuit finding for in-context learning","created":"2025-04-18","cited_by_count":5,"area":"mechinterp"},{"id":"2509.09650","title":"All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens","created":"2025-09-11","cited_by_count":5,"area":null},{"id":"2602.22968","title":"Certified Circuits: Stability Guarantees for Mechanistic Circuits","created":"2026-02-26","cited_by_count":5,"area":"mechinterp"},{"id":"2410.00340","title":"Sparse Attention Decomposition Applied to Circuit Tracing","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2410.06024","title":"Jet Expansions of Residual Computation","created":"2024-10-08","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":"2504.10077","title":"Towards Quantifying Commonsense Reasoning with Mechanistic Insights","created":"2025-04-14","cited_by_count":4,"area":"lr"},{"id":"2506.17052","title":"From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers","created":"2025-06-20","cited_by_count":4,"area":null},{"id":"2510.25117","title":"A Survey on Unlearning in Large Language Models","created":"2025-10-29","cited_by_count":4,"area":"safety"},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"},{"id":"2604.12151","title":"Distinct mechanisms underlying in-context learning in transformers","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2605.05076","title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2605.06076","title":"Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training","created":"2026-05-07","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":"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":"2408.12959","title":"Multimodal Contrastive In-Context Learning","created":"2024-08-23","cited_by_count":3,"area":null}],"next_cursor":"100"}