{"total":53,"rows":[{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"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":"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":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"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":"2410.14155","title":"Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models","created":"2024-10-18","cited_by_count":14,"area":"mechinterp"},{"id":"2505.24650","title":"Beyond the Black Box: Interpretability of LLMs in Finance","created":"2025-05-14","cited_by_count":11,"area":"mechinterp"},{"id":"2311.01732","title":"Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models","created":"2023-11-03","cited_by_count":7,"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":"2411.00173","title":"Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning","created":"2024-10-31","cited_by_count":5,"area":"mechinterp"},{"id":"2509.00749","title":"Causal Interpretation of Sparse Autoencoder Features in Vision","created":"2025-08-31","cited_by_count":5,"area":"mechinterp"},{"id":"2409.10504","title":"DILA: Dictionary Label Attention for Mechanistic Interpretability in High-dimensional Multi-label Medical Coding Prediction","created":"2024-09-16","cited_by_count":4,"area":"mechinterp"},{"id":"2604.16042","title":"Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures","created":"2026-04-17","cited_by_count":4,"area":"mechinterp"},{"id":"2409.10245","title":"From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs","created":"2024-09-16","cited_by_count":3,"area":"mechinterp"},{"id":"2410.21815","title":"Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers","created":"2024-10-29","cited_by_count":3,"area":"mechinterp"},{"id":"2501.18887","title":"Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability","created":"2025-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2505.07856","title":"Unpacking Robustness in Inflectional Languages: Adversarial Evaluation and Mechanistic Insights","created":"2025-05-08","cited_by_count":3,"area":"mechinterp"},{"id":"2507.03668","title":"TRACE: Training and Inference-Time Interpretability Analysis for Language Models","created":"2025-07-04","cited_by_count":3,"area":"mechinterp"},{"id":"2511.21514","title":"Mechanistic Interpretability for Transformer-based Time Series Classification","created":"2025-11-26","cited_by_count":3,"area":"mechinterp"},{"id":"2512.05534","title":"A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima","created":"2025-12-05","cited_by_count":3,"area":"mechinterp"},{"id":"2606.06664","title":"Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers","created":"2026-06-04","cited_by_count":3,"area":"mechinterp"},{"id":"2504.13763","title":"Decoding Vision Transformers: the Diffusion Steering Lens","created":"2025-04-18","cited_by_count":2,"area":"mechinterp"},{"id":"2505.12509","title":"Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models","created":"2025-05-18","cited_by_count":2,"area":"mechinterp"},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2604.17761","title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","created":"2026-04-20","cited_by_count":2,"area":"mechinterp"},{"id":"2607.14123","title":"Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods","created":"2026-06-18","cited_by_count":2,"area":"mechinterp"},{"id":"2608.19338","title":"Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability","created":"2026-08-19","cited_by_count":2,"area":"mechinterp"},{"id":"2307.09836","title":"Near-Linear Time Projection onto the $\\ell_{1,\\infty}$ Ball; Application to Sparse Autoencoders","created":"2023-07-19","cited_by_count":1,"area":"mechinterp"},{"id":"2409.01610","title":"Decompose the model: Mechanistic interpretability in image models with Generalized Integrated Gradients (GIG)","created":"2024-09-03","cited_by_count":1,"area":"mechinterp"},{"id":"2411.12589","title":"ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation","created":"2024-11-15","cited_by_count":1,"area":"mechinterp"},{"id":"2503.05522","title":"Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations","created":"2025-03-07","cited_by_count":1,"area":"mechinterp"},{"id":"2509.25247","title":"Protocode: Prototype-Driven Interpretability for Code Generation in LLMs","created":"2025-09-27","cited_by_count":1,"area":"mechinterp"},{"id":"2510.18462","title":"DePass: Unified Feature Attributing by Simple Decomposed Forward Pass","created":"2025-10-21","cited_by_count":1,"area":"mechinterp"},{"id":"2602.02726","title":"Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery","created":"2026-02-02","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":"2605.00474","title":"From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models","created":"2026-05-01","cited_by_count":1,"area":"mechinterp"},{"id":"2605.01829","title":"GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models","created":"2026-05-03","cited_by_count":1,"area":"mechinterp"},{"id":"2410.14506","title":"SignAttention: On the Interpretability of Transformer Models for Sign Language Translation","created":"2024-10-18","cited_by_count":0,"area":"mechinterp"},{"id":"2502.15090","title":"ExpertLens: Activation steering features are highly interpretable","created":"2025-02-20","cited_by_count":0,"area":"mechinterp"},{"id":"2509.24808","title":"Query Circuits: Explaining How Language Models Answer User Prompts","created":"2025-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2510.02734","title":"SAE-RNA: A Sparse Autoencoder Model for Interpreting RNA Language Model Representations","created":"2025-10-03","cited_by_count":0,"area":"mechinterp"},{"id":"2601.09776","title":"TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models","created":"2026-01-14","cited_by_count":0,"area":"mechinterp"},{"id":"2602.03506","title":"Explaining the Explainer: Understanding the Inner Workings of Transformer-based Symbolic Regression Models","created":"2026-02-03","cited_by_count":0,"area":"mechinterp"},{"id":"2605.04072","title":"Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction","created":"2026-04-13","cited_by_count":0,"area":"mechinterp"},{"id":"2608.20117","title":"SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events","created":"2026-08-20","cited_by_count":0,"area":"mechinterp"},{"id":"2609.07061","title":"PhysSAE: Mechanistic Interpretability of PINNs with Sparse Autoencoders","created":"2026-09-07","cited_by_count":0,"area":"mechinterp"},{"id":"2609.09055","title":"\"World Knowledge\" in the Weights: Reading Concept Circuits of Vision Transformers","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.15533","title":"The Misery of Mechanistic Interpretability: A Formal Perspective","created":"2026-09-14","cited_by_count":0,"area":"mechinterp"},{"id":"2609.17152","title":"ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers","created":"2026-09-15","cited_by_count":0,"area":"mechinterp"},{"id":"2609.30287","title":"A Mechanistic Study of AI-Text Detection Neurons in Frozen BERT: Sparse Probing and Activation Patching on RAID","created":"2026-09-08","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":"2610.17898","title":"Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features","created":"2026-10-13","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}