{"list":"other","total":51,"rows":[{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"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":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"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":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147},{"id":"2410.20526","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","created":"2024-10-27","cited_by_count":143},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97},{"id":"2307.08678","title":"Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations","created":"2023-07-17","cited_by_count":85},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81},{"id":"2404.12259","title":"Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM","created":"2024-04-18","cited_by_count":78},{"id":"2311.07466","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","created":"2023-11-13","cited_by_count":73},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62},{"id":"2305.13749","title":"Goal-Driven Explainable Clustering via Language Descriptions","created":"2023-05-23","cited_by_count":58},{"id":"2205.07237","title":"Discovering Latent Concepts Learned in BERT","created":"2022-05-15","cited_by_count":56},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41},{"id":"2309.03886","title":"FIND: A Function Description Benchmark for Evaluating Interpretability Methods","created":"2023-09-07","cited_by_count":32},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32},{"id":"2501.17727","title":"Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers","created":"2025-01-29","cited_by_count":30},{"id":"2402.14897","title":"Chain-of-Thought Unfaithfulness as Disguised Accuracy","created":"2024-02-22","cited_by_count":28},{"id":"2502.07586","title":"We Can't Understand AI Using our Existing Vocabulary","created":"2025-02-11","cited_by_count":25},{"id":"2405.20331","title":"CoSy: Evaluating Textual Explanations of Neurons","created":"2024-05-30","cited_by_count":17},{"id":"2412.11965","title":"Inferring Functionality of Attention Heads from their Parameters","created":"2024-12-16","cited_by_count":17},{"id":"2411.00743","title":"Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models","created":"2024-11-01","cited_by_count":16},{"id":"2310.11884","title":"From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks","created":"2023-10-18","cited_by_count":13},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13},{"id":"2502.16994","title":"FADE: Why Bad Descriptions Happen to Good Features","created":"2025-02-24","cited_by_count":13},{"id":"2310.06200","title":"The Importance of Prompt Tuning for Automated Neuron Explanations","created":"2023-10-09","cited_by_count":12},{"id":"2310.13439","title":"Self-Consistency of Large Language Models under Ambiguity","created":"2023-10-20","cited_by_count":12},{"id":"2402.15055","title":"Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions","created":"2024-02-23","cited_by_count":12},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11},{"id":"2404.18533","title":"Evaluating Readability and Faithfulness of Concept-based Explanations","created":"2024-04-29","cited_by_count":10},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9},{"id":"2502.12483","title":"The Knowledge Microscope: Features as Better Analytical Lenses than Neurons","created":"2025-02-18","cited_by_count":5},{"id":"2505.20293","title":"Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery","created":"2025-05-26","cited_by_count":1}],"next_cursor":null}