{"total":64,"rows":[{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"area":"mechinterp"},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"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":"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":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209,"area":"mechinterp"},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205,"area":"mechinterp"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149,"area":null},{"id":"2109.09234","title":"Conditional probing: measuring usable information beyond a baseline","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2406.16778","title":"Finding Transformer Circuits with Edge Pruning","created":"2024-06-24","cited_by_count":60,"area":null},{"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":"2507.06952","title":"What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models","created":"2025-07-09","cited_by_count":47,"area":"wm"},{"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":"2511.13653","title":"Weight-sparse transformers have interpretable circuits","created":"2025-11-17","cited_by_count":44,"area":"mechinterp"},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29,"area":null},{"id":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2407.14494","title":"InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques","created":"2024-07-19","cited_by_count":25,"area":"mechinterp"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2310.03084","title":"Discovering Knowledge-Critical Subnetworks in Pretrained Language Models","created":"2023-10-04","cited_by_count":16,"area":null},{"id":"2506.20790","title":"Stochastic Parameter Decomposition","created":"2025-06-25","cited_by_count":16,"area":null},{"id":"2405.12522","title":"Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models","created":"2024-05-21","cited_by_count":15,"area":"mechinterp"},{"id":"2407.03779","title":"Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity","created":"2024-07-04","cited_by_count":14,"area":null},{"id":"2404.14349","title":"Automatic Discovery of Visual Circuits","created":"2024-04-22","cited_by_count":13,"area":null},{"id":"2311.04354","title":"Uncovering Intermediate Variables in Transformers using Circuit Probing","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2410.01434","title":"Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2309.00244","title":"NeuroSurgeon: A Toolkit for Subnetwork Analysis","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2602.00038","title":"LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion","created":"2026-01-19","cited_by_count":8,"area":"alignment"},{"id":"2205.11833","title":"Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2207.01736","title":"Probing via Prompting","created":"2022-07-04","cited_by_count":7,"area":null},{"id":"2211.04281","title":"SocioProbe: What, When, and Where Language Models Learn about Sociodemographics","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2406.16563","title":"Are there identifiable structural parts in the sentence embedding whole?","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2407.18119","title":"Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification","created":"2024-07-25","cited_by_count":6,"area":null},{"id":"2502.15277","title":"Analyzing the Inner Workings of Transformers in Compositional Generalization","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2506.04706","title":"Line of Sight: On Linear Representations in VLLMs","created":"2025-06-05","cited_by_count":6,"area":"mechinterp"},{"id":"2604.04982","title":"CURE:Circuit-Aware Unlearning for LLM-based Recommendation","created":"2026-04-04","cited_by_count":6,"area":"safety"},{"id":"2211.06420","title":"The Architectural Bottleneck Principle","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2407.14008","title":"Investigating the Indirect Object Identification circuit in Mamba","created":"2024-07-19","cited_by_count":5,"area":"ssm"},{"id":"2510.03282","title":"Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework","created":"2025-09-28","cited_by_count":4,"area":"mechinterp"},{"id":"2603.23268","title":"SafeSeek: Universal Attribution of Safety Circuits in Language Models","created":"2026-03-24","cited_by_count":4,"area":"safety"},{"id":"2108.13602","title":"How Does Adversarial Fine-Tuning Benefit BERT?","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2403.11747","title":"Embedded Named Entity Recognition using Probing Classifiers","created":"2024-03-18","cited_by_count":3,"area":null},{"id":"2501.18887","title":"Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability","created":"2025-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2509.21631","title":"Towards Transparent AI: A Survey on Explainable Language Models","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.23264","title":"PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization","created":"2025-10-27","cited_by_count":3,"area":"mechinterp"},{"id":"2602.22581","title":"IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck","created":"2026-02-26","cited_by_count":3,"area":"mechinterp"},{"id":"2210.07071","title":"The Open-World Lottery Ticket Hypothesis for OOD Intent Classification","created":"2022-10-13","cited_by_count":2,"area":null},{"id":"2310.04519","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2606.16939","title":"Scalable Circuit Learning for Interpreting Large Language Models","created":"2026-06-15","cited_by_count":2,"area":"mechinterp"},{"id":"2203.15860","title":"Visualizing the Relationship Between Encoded Linguistic Information and Task Performance","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2508.16109","title":"From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits","created":"2025-08-22","cited_by_count":1,"area":"mechinterp"},{"id":"2605.26343","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2409.16292","title":"Explaining Human Comparisons using Alignment-Importance Heatmaps","created":"2024-09-08","cited_by_count":0,"area":null},{"id":"2507.18550","title":"On the Performance of Concept Probing: The Influence of the Data (Extended Version)","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2507.18681","title":"Concept Probing: Where to Find Human-Defined Concepts (Extended Version)","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2510.18636","title":"C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2603.15919","title":"Sparse but not Simpler: A Multi-Level Interpretability Analysis of Vision Transformers","created":"2026-03-16","cited_by_count":0,"area":"mechinterp"},{"id":"2605.06632","title":"Crafting Reversible SFT Behaviors in Large Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.08536","title":"Can Graph Learning Learn Circuits?","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2608.27504","title":"Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability Study","created":"2026-08-27","cited_by_count":0,"area":"alignment"},{"id":"2609.35108","title":"A mechanistic study of language model introspection","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}