{"total":22,"rows":[{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212,"area":null},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"area":null},{"id":"2406.09265","title":"Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs","created":"2024-06-13","cited_by_count":33,"area":null},{"id":"2504.12459","title":"On Linear Representations and Pretraining Data Frequency in Language Models","created":"2025-04-16","cited_by_count":23,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2409.13714","title":"TracrBench: Generating Interpretability Testbeds with Large Language Models","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2409.17113","title":"Characterizing stable regions in the residual stream of LLMs","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2505.24293","title":"Equivalent Linear Mappings of Large Language Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2402.02407","title":"Defining Neural Network Architecture through Polytope Structures of Dataset","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2404.06104","title":"A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes","created":"2024-04-09","cited_by_count":2,"area":null},{"id":"2406.03947","title":"Weight-based Decomposition: A Case for Bilinear MLPs","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2501.16374","title":"SAFR: Neuron Redistribution for Interpretability","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2505.22798","title":"Efficient Preimage Approximation for Neural Network Certification","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2509.23893","title":"Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2307.00721","title":"Neural Polytopes","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2505.11576","title":"Concept-Guided Interpretability via Neural Chunking","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2602.07930","title":"Patches of Nonlinearity: Instruction Vectors in Large Language Models","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2607.08946","title":"Training, Reading, and Editing Legible Transformers","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2506.04360","title":"Even Faster Hyperbolic Random Forests: A Beltrami-Klein Wrapper Approach","created":"2025-06-04","cited_by_count":0,"area":null}],"next_cursor":null}