{"total":20,"rows":[{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"area":"mechinterp"},{"id":"2508.16560","title":"Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders","created":"2025-08-22","cited_by_count":14,"area":"mechinterp"},{"id":"2411.02124","title":"Adaptive Sparse Allocation with Mutual Choice & Feature Choice Sparse Autoencoders","created":"2024-11-04","cited_by_count":9,"area":"mechinterp"},{"id":"2503.03032","title":"SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs","created":"2025-03-04","cited_by_count":8,"area":"mechinterp"},{"id":"2512.13568","title":"Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability","created":"2025-12-15","cited_by_count":7,"area":"mechinterp"},{"id":"2505.00808","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","created":"2025-05-01","cited_by_count":6,"area":"mechinterp"},{"id":"2507.08473","title":"Evaluating SAE interpretability without explanations","created":"2025-07-11","cited_by_count":5,"area":"mechinterp"},{"id":"2510.16820","title":"Finding Manifolds With Bilinear Autoencoders","created":"2025-10-19","cited_by_count":5,"area":"mechinterp"},{"id":"2603.04198","title":"Stable and Steerable Sparse Autoencoders with Weight Regularization","created":"2026-03-04","cited_by_count":5,"area":"mechinterp"},{"id":"2505.24473","title":"Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy","created":"2025-05-30","cited_by_count":4,"area":"mechinterp"},{"id":"2605.07922","title":"Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders","created":"2026-05-08","cited_by_count":4,"area":"mechinterp"},{"id":"2509.25596","title":"Binary Sparse Coding for Interpretability","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2605.14694","title":"The Rate-Distortion-Polysemanticity Tradeoff in SAEs","created":"2026-05-14","cited_by_count":3,"area":"mechinterp"},{"id":"2505.01372","title":"Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii","created":"2025-05-02","cited_by_count":2,"area":"mechinterp"},{"id":"2506.17673","title":"FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies","created":"2025-06-21","cited_by_count":2,"area":"mechinterp"},{"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":"2605.08891","title":"Bilinear autoencoders find interpretable manifolds","created":"2026-05-09","cited_by_count":1,"area":"mechinterp"},{"id":"2607.17425","title":"Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?","created":"2026-07-19","cited_by_count":0,"area":"mechinterp"},{"id":"2610.04112","title":"The Independence Prior of SAEs Fragments Visual Concepts","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}