{"total":86,"rows":[{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032,"area":"safety"},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553,"area":"mechinterp"},{"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":"2503.17547","title":"Learning Multi-Level Features with Matryoshka Sparse Autoencoders","created":"2025-03-21","cited_by_count":143,"area":"mechinterp"},{"id":"2503.09532","title":"SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability","created":"2025-03-12","cited_by_count":124,"area":"mechinterp"},{"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":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"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":"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":"2408.00113","title":"Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models","created":"2024-07-31","cited_by_count":51,"area":"mechinterp"},{"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":"2406.17759","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","created":"2024-06-25","cited_by_count":43,"area":"mechinterp"},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"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":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"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":"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":"2408.00657","title":"Disentangling Dense Embeddings with Sparse Autoencoders","created":"2024-08-01","cited_by_count":23,"area":"mechinterp"},{"id":"2411.13117","title":"Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders","created":"2024-11-20","cited_by_count":18,"area":"mechinterp"},{"id":"2501.06254","title":"Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words","created":"2025-01-09","cited_by_count":18,"area":"lr"},{"id":"2410.11767","title":"Analyzing (In)Abilities of SAEs via Formal Languages","created":"2024-10-15","cited_by_count":17,"area":"mechinterp"},{"id":"2411.00743","title":"Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models","created":"2024-11-01","cited_by_count":16,"area":"mechinterp"},{"id":"2503.03601","title":"Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders","created":"2025-03-05","cited_by_count":15,"area":"mechinterp"},{"id":"2502.16994","title":"FADE: Why Bad Descriptions Happen to Good Features","created":"2025-02-24","cited_by_count":13,"area":"mechinterp"},{"id":"2505.16004","title":"Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders","created":"2025-05-21","cited_by_count":12,"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":"2502.19964","title":"Do Sparse Autoencoders Generalize? A Case Study of Answerability","created":"2025-02-27","cited_by_count":8,"area":"mechinterp"},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2410.22517","title":"Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models","created":"2024-10-29","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":"2509.23323","title":"LLM Interpretability with Identifiable Temporal-Instantaneous Representation","created":"2025-09-27","cited_by_count":6,"area":"mechinterp"},{"id":"2405.14277","title":"Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2411.06424","title":"How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis","created":"2024-11-10","cited_by_count":5,"area":"alignment"},{"id":"2509.23717","title":"Measuring Sparse Autoencoder Feature Sensitivity","created":"2025-09-28","cited_by_count":4,"area":"mechinterp"},{"id":"2510.11210","title":"Discursive Circuits: How Do Language Models Understand Discourse Relations?","created":"2025-10-13","cited_by_count":4,"area":"mechinterp"},{"id":"2605.18229","title":"Are Sparse Autoencoder Benchmarks Reliable?","created":"2026-05-18","cited_by_count":4,"area":"mechinterp"},{"id":"2605.29889","title":"Where Do Apparent LLM Clinical Triage Failures Arise? Localizing the Multiple-Choice Format Effect","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2606.11722","title":"ICA Lens: Interpreting Language Models Without Training Another Dictionary","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2505.17769","title":"Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2508.09363","title":"Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders","created":"2025-08-12","cited_by_count":3,"area":"lr"},{"id":"2605.31183","title":"Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines","created":"2026-05-29","cited_by_count":3,"area":"mechinterp"},{"id":"2410.07456","title":"SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders","created":"2024-10-09","cited_by_count":2,"area":"mechinterp"},{"id":"2506.07406","title":"InverseScope: Scalable Activation Inversion for Interpreting Large Language Models","created":"2025-06-09","cited_by_count":2,"area":"mechinterp"},{"id":"2507.00163","title":"Prompting as Scientific Inquiry","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2507.12202","title":"Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control","created":"2025-07-16","cited_by_count":2,"area":"mechinterp"},{"id":"2507.15227","title":"Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders","created":"2025-07-21","cited_by_count":2,"area":"mechinterp"},{"id":"2512.19115","title":"Generative Giants, Retrieval Weaklings: Why do Multimodal Large Language Models Fail at Multimodal Retrieval?","created":"2025-12-22","cited_by_count":2,"area":"mllm"},{"id":"2605.12874","title":"Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features","created":"2026-05-13","cited_by_count":2,"area":"mechinterp"},{"id":"2605.23035","title":"Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography","created":"2026-05-21","cited_by_count":2,"area":"alignment"},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2609.18080","title":"Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition","created":"2026-09-16","cited_by_count":2,"area":"mechinterp"},{"id":"2507.00269","title":"Feature Integration Spaces: Joint Training Reveals Dual Encoding in Neural Network Representations","created":"2025-06-30","cited_by_count":1,"area":"mechinterp"},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2509.25690","title":"A Unified Probabilistic Framework for Dictionary Learning with Parsimonious Activation","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2511.00029","title":"Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts","created":"2025-10-26","cited_by_count":1,"area":"mechinterp"},{"id":"2511.18024","title":"Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2601.20425","title":"Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.12403","title":"MonoLoss: A Training Objective for Interpretable Monosemantic Representations","created":"2026-02-12","cited_by_count":1,"area":"mechinterp"},{"id":"2606.18322","title":"SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior","created":"2026-06-16","cited_by_count":1,"area":"mechinterp"},{"id":"2607.07316","title":"Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2607.16789","title":"MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning","created":"2026-07-18","cited_by_count":1,"area":null},{"id":"2607.20596","title":"Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects","created":"2026-07-22","cited_by_count":1,"area":"mechinterp"},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.06862","title":"Feature Superposition in Neural Networks: From Theory to Practice","created":"2026-09-06","cited_by_count":1,"area":"mechinterp"},{"id":"2411.18502","title":"Isometry pursuit","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2505.00190","title":"Empirical Evaluation of Progressive Coding for Sparse Autoencoders","created":"2025-04-30","cited_by_count":0,"area":"mechinterp"},{"id":"2601.20420","title":"Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs","created":"2026-01-28","cited_by_count":0,"area":"mechinterp"},{"id":"2601.23153","title":"Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic Data","created":"2026-01-30","cited_by_count":0,"area":"synth"},{"id":"2602.00924","title":"Supervised sparse auto-encoders for interpretable and compositional representations","created":"2026-01-31","cited_by_count":0,"area":"mechinterp"},{"id":"2604.20945","title":"Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs","created":"2026-04-22","cited_by_count":0,"area":"safety"},{"id":"2605.18789","title":"Features have life history. And we should care","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.28149","title":"Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations","created":"2026-05-27","cited_by_count":0,"area":"mechinterp"},{"id":"2606.17010","title":"From Tokens to Policy: Causal and Interpretable Heterogeneous Treatment Effects Identification","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.19386","title":"Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance","created":"2026-07-01","cited_by_count":0,"area":"mechinterp"},{"id":"2607.20652","title":"Scaling Interpretable Transformers with Parity Bottleneck Layers","created":"2026-07-22","cited_by_count":0,"area":"mechinterp"},{"id":"2607.27404","title":"ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.13337","title":"Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation","created":"2026-08-13","cited_by_count":0,"area":"mechinterp"},{"id":"2608.29034","title":"A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability","created":"2026-08-29","cited_by_count":0,"area":"mechinterp"},{"id":"2609.04344","title":"SharedSAE: One Feature Dictionary Across Language Models","created":"2026-09-03","cited_by_count":0,"area":"mechinterp"},{"id":"2609.22695","title":"A Survey on the Linear Representation Hypothesis","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.29328","title":"Grammatical \"grandmother neurons\" are rare in LLMs","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36294","title":"When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2609.37857","title":"Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2610.20139","title":"Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility","created":"2026-10-14","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}