{"total":40,"rows":[{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085,"area":"mechinterp"},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839,"area":"mechinterp"},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209,"area":"mechinterp"},{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"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":"2412.12101","title":"InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders","created":"2024-11-13","cited_by_count":66,"area":"mechinterp"},{"id":"2306.01128","title":"Learning Transformer Programs","created":"2023-06-01","cited_by_count":41,"area":"mechinterp"},{"id":"2410.17245","title":"Towards Reliable Evaluation of Behavior Steering Interventions in LLMs","created":"2024-10-22","cited_by_count":36,"area":"mechinterp"},{"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":"2503.05213","title":"Personalized Text Generation with Contrastive Activation Steering","created":"2025-03-07","cited_by_count":34,"area":"mechinterp"},{"id":"2502.18862","title":"One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs","created":"2025-02-26","cited_by_count":29,"area":"mechinterp"},{"id":"2410.03334","title":"An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation","created":"2024-10-04","cited_by_count":25,"area":"mechinterp"},{"id":"2406.11779","title":"Compact Proofs of Model Performance via Mechanistic Interpretability","created":"2024-06-17","cited_by_count":18,"area":"mechinterp"},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2405.04156","title":"How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability","created":"2024-05-07","cited_by_count":14,"area":"mechinterp"},{"id":"2407.19842","title":"Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability","created":"2024-07-29","cited_by_count":13,"area":"mechinterp"},{"id":"2510.13285","title":"In-Distribution Steering: Balancing Control and Coherence in Language Model Generation","created":"2025-10-15","cited_by_count":9,"area":"mechinterp"},{"id":"2203.12971","title":"Probing for Labeled Dependency Trees","created":"2022-03-24","cited_by_count":8,"area":"mechinterp"},{"id":"2508.01916","title":"Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning","created":"2025-08-03","cited_by_count":8,"area":"mechinterp"},{"id":"2501.19066","title":"Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations","created":"2025-01-31","cited_by_count":7,"area":"mechinterp"},{"id":"2511.20273","title":"Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits","created":"2025-11-25","cited_by_count":7,"area":"mechinterp"},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2204.07023","title":"Composite Code Sparse Autoencoders for first stage retrieval","created":"2022-04-14","cited_by_count":4,"area":"mechinterp"},{"id":"2412.15750","title":"Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference","created":"2024-12-20","cited_by_count":3,"area":"mechinterp"},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2507.18512","title":"Explaining How Visual, Textual and Multimodal Encoders Share Concepts","created":"2025-07-24","cited_by_count":1,"area":"mechinterp"},{"id":"2510.25013","title":"Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers","created":"2025-10-28","cited_by_count":1,"area":"mechinterp"},{"id":"2511.15572","title":"From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers","created":"2025-11-19","cited_by_count":1,"area":"mechinterp"},{"id":"2512.15938","title":"SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks","created":"2025-12-17","cited_by_count":1,"area":"mechinterp"},{"id":"2602.12403","title":"MonoLoss: A Training Objective for Interpretable Monosemantic Representations","created":"2026-02-12","cited_by_count":1,"area":"mechinterp"},{"id":"2603.01752","title":"Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence","created":"2026-03-02","cited_by_count":1,"area":"mechinterp"},{"id":"2603.13259","title":"How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing","created":"2026-02-25","cited_by_count":1,"area":"mechinterp"},{"id":"2605.21303","title":"From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach","created":"2026-05-20","cited_by_count":1,"area":"mechinterp"},{"id":"2511.09432","title":"Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data","created":"2025-11-12","cited_by_count":0,"area":"mechinterp"},{"id":"2512.11090","title":"Data-Driven Model Reduction using WeldNet: Windowed Encoders for Learning Dynamics","created":"2025-12-11","cited_by_count":0,"area":"mechinterp"},{"id":"2606.24903","title":"The Geometry of Saturation: Effective Rank Predicts When Labels Stop Helping in Few-Shot Classification","created":"2026-06-12","cited_by_count":0,"area":"mechinterp"},{"id":"2608.08383","title":"Safety Cost of Steering Vectors Is Separable and Reducible","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2608.22034","title":"Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation","created":"2026-08-22","cited_by_count":0,"area":"mechinterp"},{"id":"2609.14151","title":"Signatures of Steerability in Activation Space of Language Models","created":"2026-09-12","cited_by_count":0,"area":"mechinterp"},{"id":"2610.02829","title":"Clinical Concept Centers in LLMs","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}