{"list":"other","total":61,"rows":[{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308},{"id":"2305.16367","title":"Role-Play with Large Language Models","created":"2023-05-25","cited_by_count":294},{"id":"2304.08247","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","created":"2023-04-14","cited_by_count":286},{"id":"2011.14878","title":"Explaining by Removing: A Unified Framework for Model Explanation","created":"2020-11-21","cited_by_count":218},{"id":"1312.5663","title":"k-Sparse Autoencoders","created":"2013-12-19","cited_by_count":215},{"id":"2106.07682","title":"Revisiting Model Stitching to Compare Neural Representations","created":"2021-06-14","cited_by_count":209},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"1905.05824","title":"Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models","created":"2019-05-14","cited_by_count":117},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78},{"id":"2210.01892","title":"Polysemanticity and Capacity in Neural Networks","created":"2022-10-04","cited_by_count":77},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73},{"id":"2403.15498","title":"Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models","created":"2024-03-21","cited_by_count":62},{"id":"1804.06620","title":"Visualizing the Feature Importance for Black Box Models","created":"2018-04-18","cited_by_count":55},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33},{"id":"2304.09707","title":"Disentangling Neuron Representations with Concept Vectors","created":"2023-04-19","cited_by_count":28},{"id":"2410.03334","title":"An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation","created":"2024-10-04","cited_by_count":25},{"id":"2312.08550","title":"Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks","created":"2023-12-13","cited_by_count":23},{"id":"2312.02566","title":"Structured World Representations in Maze-Solving Transformers","created":"2023-12-05","cited_by_count":16},{"id":"2311.08968","title":"Identifying Linear Relational Concepts in Large Language Models","created":"2023-11-15","cited_by_count":12},{"id":"2212.11415","title":"Circumventing interpretability: How to defeat mind-readers","created":"2022-12-21","cited_by_count":6},{"id":"2310.07837","title":"Measuring Feature Sparsity in Language Models","created":"2023-10-11","cited_by_count":3}],"next_cursor":null}