{"total":55,"rows":[{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420,"area":"mechinterp"},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2405.08366","title":"Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control","created":"2024-05-14","cited_by_count":86,"area":"mechinterp"},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"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":"2208.10431","title":"ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition","created":"2022-08-22","cited_by_count":63,"area":null},{"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":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59,"area":null},{"id":"2406.17759","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","created":"2024-06-25","cited_by_count":43,"area":"mechinterp"},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2402.12201","title":"Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT","created":"2024-02-19","cited_by_count":29,"area":"mechinterp"},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2502.06755","title":"Interpretable and Testable Vision Features via Sparse Autoencoders","created":"2025-02-10","cited_by_count":25,"area":"mechinterp"},{"id":"2405.13868","title":"Automatically Identifying Local and Global Circuits with Linear Computation Graphs","created":"2024-05-22","cited_by_count":24,"area":"mechinterp"},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2205.00756","title":"VICE: Variational Interpretable Concept Embeddings","created":"2022-05-02","cited_by_count":15,"area":null},{"id":"2301.00709","title":"Tsetlin Machine Embedding: Representing Words Using Logical Expressions","created":"2023-01-02","cited_by_count":15,"area":null},{"id":"2202.03753","title":"Semantic features of object concepts generated with GPT-3","created":"2022-02-08","cited_by_count":12,"area":null},{"id":"2312.15033","title":"Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention","created":"2023-12-22","cited_by_count":12,"area":null},{"id":"2406.17969","title":"Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective","created":"2024-06-25","cited_by_count":10,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2503.00723","title":"Re-Imagining Multimodal Instruction Tuning: A Representation View","created":"2025-03-02","cited_by_count":9,"area":"mllm"},{"id":"2310.01162","title":"DINE: Dimensional Interpretability of Node Embeddings","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2506.13831","title":"Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation","created":"2025-06-16","cited_by_count":6,"area":null},{"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":"2406.10984","title":"Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"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":"2507.08473","title":"Evaluating SAE interpretability without explanations","created":"2025-07-11","cited_by_count":5,"area":"mechinterp"},{"id":"2106.09502","title":"Biomedical Interpretable Entity Representations","created":"2021-06-17","cited_by_count":4,"area":null},{"id":"2303.00333","title":"Competence-Based Analysis of Language Models","created":"2023-03-01","cited_by_count":4,"area":null},{"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":"2203.13901","title":"AUTOLEX: An Automatic Framework for Linguistic Exploration","created":"2022-03-25","cited_by_count":3,"area":null},{"id":"2209.03450","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2311.11491","title":"On the Relationship Between Interpretability and Explainability in Machine Learning","created":"2023-11-20","cited_by_count":3,"area":null},{"id":"2504.14766","title":"Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2310.12751","title":"Character-level Chinese Backpack Language Models","created":"2023-10-19","cited_by_count":1,"area":"mechinterp"},{"id":"2410.21043","title":"Disentangled and Self-Explainable Node Representation Learning","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2503.03129","title":"Exploring Neural Ordinary Differential Equations as Interpretable Healthcare classifiers","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2506.08427","title":"Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2103.11431","title":"SEMIE: SEMantically Infused Embeddings with Enhanced Interpretability for Domain-specific Small Corpus","created":"2021-03-21","cited_by_count":0,"area":null},{"id":"2302.12178","title":"A Scalable Space-efficient In-database Interpretability Framework for Embedding-based Semantic SQL Queries","created":"2023-02-23","cited_by_count":0,"area":null},{"id":"2306.08020","title":"Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts","created":"2023-06-13","cited_by_count":0,"area":null},{"id":"2306.14135","title":"Interpretable Neural Embeddings with Sparse Self-Representation","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2406.13385","title":"Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2412.08187","title":"From communities to interpretable network and word embedding: an unified approach","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2510.05696","title":"Sparse deepfake detection promotes better disentanglement","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2603.01945","title":"When Numbers Tell Half the Story: Human-Metric Alignment in Topic Model Evaluation","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.01619","title":"Automatic Image-Level Morphological Trait Annotation for Organismal Images","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.21305","title":"LISE : Listenable Interpretable Speaker Embeddings","created":"2026-06-19","cited_by_count":0,"area":null}],"next_cursor":null}