{"total":30,"rows":[{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2204.00616","title":"Simplicial Embeddings in Self-Supervised Learning and Downstream Classification","created":"2022-04-01","cited_by_count":24,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"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":"2301.00709","title":"Tsetlin Machine Embedding: Representing Words Using Logical Expressions","created":"2023-01-02","cited_by_count":15,"area":null},{"id":"2501.08145","title":"Refusal Behavior in Large Language Models: A Nonlinear Perspective","created":"2025-01-14","cited_by_count":13,"area":null},{"id":"2502.14862","title":"Interpretable Text Embeddings and Text Similarity Explanation: A Survey","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2301.04704","title":"SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2310.01162","title":"DINE: Dimensional Interpretability of Node Embeddings","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2104.07198","title":"Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval","created":"2021-04-15","cited_by_count":7,"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":"2406.10984","title":"Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2506.02204","title":"BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2106.09502","title":"Biomedical Interpretable Entity Representations","created":"2021-06-17","cited_by_count":4,"area":null},{"id":"2103.15330","title":"Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2310.07837","title":"Measuring Feature Sparsity in Language Models","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2111.01023","title":"Interpretable contrastive word mover's embedding","created":"2021-11-01","cited_by_count":2,"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":"2505.08348","title":"Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2507.06427","title":"Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders","created":"2025-07-08","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":"2205.13614","title":"Emergent organization of receptive fields in networks of excitatory and inhibitory neurons","created":"2022-05-26","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":"2411.08384","title":"Interpretable Syntactic Representations Enable Hierarchical Word Vectors","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2502.05407","title":"Dictionary Learning: The Complexity of Learning Sparse Superposed Features with Feedback","created":"2025-02-08","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}],"next_cursor":null}