{"total":124,"rows":[{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"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":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"area":null},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132,"area":null},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126,"area":null},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97,"area":null},{"id":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83,"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":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2404.14394","title":"A Multimodal Automated Interpretability Agent","created":"2024-04-22","cited_by_count":63,"area":"agents"},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2205.07237","title":"Discovering Latent Concepts Learned in BERT","created":"2022-05-15","cited_by_count":56,"area":null},{"id":"2405.19237","title":"ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning","created":"2024-05-29","cited_by_count":55,"area":"diffusion"},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40,"area":null},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","cited_by_count":38,"area":null},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2105.15179","title":"How transfer learning impacts linguistic knowledge in deep NLP models?","created":"2021-05-31","cited_by_count":32,"area":null},{"id":"2208.10609","title":"Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis","created":"2022-08-22","cited_by_count":32,"area":null},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2305.19911","title":"Neuron to Graph: Interpreting Language Model Neurons at Scale","created":"2023-05-31","cited_by_count":27,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2407.08582","title":"On the Universal Truthfulness Hyperplane Inside LLMs","created":"2024-07-11","cited_by_count":24,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2409.12915","title":"Exploring Representations and Interventions in Time Series Foundation Models","created":"2024-09-19","cited_by_count":20,"area":null},{"id":"2210.12696","title":"On the Transformation of Latent Space in Fine-Tuned NLP Models","created":"2022-10-23","cited_by_count":19,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2305.13386","title":"Can LLMs facilitate interpretation of pre-trained language models?","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2310.18443","title":"Towards a fuller understanding of neurons with Clustered Compositional Explanations","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2204.06201","title":"Probing for Constituency Structure in Neural Language Models","created":"2022-04-13","cited_by_count":14,"area":null},{"id":"2205.02023","title":"Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models","created":"2022-05-04","cited_by_count":14,"area":null},{"id":"2406.10868","title":"Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts","created":"2024-06-16","cited_by_count":14,"area":null},{"id":"2110.08388","title":"Probing as Quantifying Inductive Bias","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2210.09404","title":"Measures of Information Reflect Memorization Patterns","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2310.15151","title":"Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2311.15983","title":"SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2410.16930","title":"Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2107.00439","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2211.05523","title":"Impact of Adversarial Training on Robustness and Generalizability of Language Models","created":"2022-11-10","cited_by_count":9,"area":null},{"id":"2502.10927","title":"The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training","created":"2025-02-15","cited_by_count":9,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2407.04307","title":"Crafting Large Language Models for Enhanced Interpretability","created":"2024-07-05","cited_by_count":8,"area":null},{"id":"2508.02587","title":"Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules","created":"2025-08-04","cited_by_count":8,"area":"moe"},{"id":"2104.07456","title":"Effect of Post-processing on Contextualized Word Representations","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2403.04872","title":"Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2503.09046","title":"Discovering Influential Neuron Path in Vision Transformers","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2112.07806","title":"Representation Alignment in Neural Networks","created":"2021-12-15","cited_by_count":6,"area":null},{"id":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2211.06642","title":"ConceptX: A Framework for Latent Concept Analysis","created":"2022-11-12","cited_by_count":6,"area":null},{"id":"2601.03115","title":"Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2201.08214","title":"A Latent-Variable Model for Intrinsic Probing","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2305.17409","title":"On the special role of class-selective neurons in early training","created":"2023-05-27","cited_by_count":5,"area":null},{"id":"2406.02335","title":"Probing the Category of Verbal Aspect in Transformer Language Models","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2409.05910","title":"Property Neurons in Self-Supervised Speech Transformers","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2506.10920","title":"Constructing Interpretable Features from Compositional Neuron Groups","created":"2025-06-12","cited_by_count":5,"area":"mechinterp"},{"id":"2508.08274","title":"Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2509.13664","title":"Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs","created":"2025-09-17","cited_by_count":5,"area":null},{"id":"2103.00573","title":"RuSentEval: Linguistic Source, Encoder Force!","created":"2021-02-28","cited_by_count":4,"area":null},{"id":"2105.08039","title":"Fine-grained Interpretation and Causation Analysis in Deep NLP Models","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2206.00259","title":"IDANI: Inference-time Domain Adaptation via Neuron-level Interventions","created":"2022-06-01","cited_by_count":4,"area":null},{"id":"2206.10821","title":"Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2304.12918","title":"N2G: A Scalable Approach for Quantifying Interpretable Neuron Representations in Large Language Models","created":"2023-04-22","cited_by_count":4,"area":"mechinterp"},{"id":"2410.08255","title":"Investigating Representation Universality: Case Study on Genealogical Representations","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2502.17355","title":"On Relation-Specific Neurons in Large Language Models","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2508.15094","title":"Evaluating Sparse Autoencoders for Monosemantic Representation","created":"2025-08-20","cited_by_count":4,"area":"mechinterp"},{"id":"2509.17665","title":"Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models","created":"2025-09-22","cited_by_count":4,"area":"mechinterp"},{"id":"2512.00852","title":"One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces","created":"2025-11-30","cited_by_count":4,"area":null},{"id":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2402.02801","title":"KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models","created":"2024-02-05","cited_by_count":3,"area":null},{"id":"2404.02650","title":"Towards detecting unanticipated bias in Large Language Models","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2404.15848","title":"Detecting Conceptual Abstraction in LLMs","created":"2024-04-24","cited_by_count":3,"area":null},{"id":"2410.11868","title":"Neuropsychology of AI: Relationship Between Activation Proximity and Categorical Proximity Within Neural Categories of Synthetic Cognition","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2412.07947","title":"GPT-2 Through the Lens of Vector Symbolic Architectures","created":"2024-12-10","cited_by_count":3,"area":"mechinterp"},{"id":"2501.06196","title":"How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neurons","created":"2024-12-26","cited_by_count":3,"area":"lr"},{"id":"2506.00832","title":"Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2506.23951","title":"Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders","created":"2025-06-30","cited_by_count":3,"area":"mechinterp"},{"id":"2510.02296","title":"Continual Personalization for Diffusion Models","created":"2025-10-02","cited_by_count":3,"area":"diffusion"},{"id":"2510.24942","title":"Finding Culture-Sensitive Neurons in Vision-Language Models","created":"2025-10-28","cited_by_count":3,"area":"mllm"},{"id":"2110.03067","title":"On Neurons Invariant to Sentence Structural Changes in Neural Machine Translation","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2205.11702","title":"Functional Network: A Novel Framework for Interpretability of Deep Neural Networks","created":"2022-05-24","cited_by_count":2,"area":null},{"id":"2306.12314","title":"Introspective Action Advising for Interpretable Transfer Learning","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2411.18651","title":"Verbalized Representation Learning for Interpretable Few-Shot Generalization","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2503.05280","title":"Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing","created":"2025-03-07","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":"2506.20040","title":"Cross-Layer Discrete Concept Discovery for Interpreting Language Models","created":"2025-06-24","cited_by_count":2,"area":"mechinterp"},{"id":"2603.17231","title":"Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2104.00789","title":"Do RNN States Encode Abstract Phonological Processes?","created":"2021-04-01","cited_by_count":1,"area":null}],"next_cursor":"100"}