{"total":108,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"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":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2403.00745","title":"AtP*: An efficient and scalable method for localizing LLM behaviour to components","created":"2024-03-01","cited_by_count":111,"area":"mechinterp"},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79,"area":"mechinterp"},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79,"area":"lr"},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2406.19501","title":"Monitoring Latent World States in Language Models with Propositional Probes","created":"2024-06-27","cited_by_count":43,"area":"wm"},{"id":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"area":null},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2502.20332","title":"Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":31,"area":"lr"},{"id":"2409.05448","title":"Representational Analysis of Binding in Language Models","created":"2024-09-09","cited_by_count":28,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2510.06182","title":"Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context","created":"2025-10-07","cited_by_count":26,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2407.00886","title":"Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition","created":"2024-07-01","cited_by_count":23,"area":"mechinterp"},{"id":"2407.14662","title":"Relational Composition in Neural Networks: A Survey and Call to Action","created":"2024-07-19","cited_by_count":23,"area":null},{"id":"2502.13913","title":"How Do LLMs Perform Two-Hop Reasoning in Context?","created":"2025-02-19","cited_by_count":20,"area":"lr"},{"id":"2510.24709","title":"Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?","created":"2025-10-28","cited_by_count":19,"area":null},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2405.15302","title":"Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism","created":"2024-05-24","cited_by_count":15,"area":"lr"},{"id":"2402.02212","title":"A Survey to Recent Progress Towards Understanding In-Context Learning","created":"2024-02-03","cited_by_count":14,"area":null},{"id":"2404.13070","title":"Evidence from counterfactual tasks supports emergent analogical reasoning in large language models","created":"2024-04-14","cited_by_count":14,"area":"lr"},{"id":"2502.17955","title":"Language Models' Factuality Depends on the Language of Inquiry","created":"2025-02-25","cited_by_count":14,"area":null},{"id":"2601.12626","title":"Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models","created":"2026-01-18","cited_by_count":14,"area":"lr"},{"id":"2406.15955","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","created":"2024-06-22","cited_by_count":13,"area":null},{"id":"2504.01928","title":"Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure","created":"2025-04-02","cited_by_count":13,"area":null},{"id":"2506.15871","title":"Visual symbolic mechanisms: Emergent symbol processing in vision language models","created":"2025-06-18","cited_by_count":13,"area":"mllm"},{"id":"2410.22590","title":"Characterizing the Role of Similarity in the Property Inferences of Language Models","created":"2024-10-29","cited_by_count":11,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2502.04667","title":"Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning","created":"2025-02-07","cited_by_count":10,"area":"lr"},{"id":"2408.14915","title":"Can Transformers Do Enumerative Geometry?","created":"2024-08-27","cited_by_count":8,"area":null},{"id":"2505.05145","title":"Understanding In-context Learning of Addition via Activation Subspaces","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2510.01025","title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2602.22424","title":"Causality $\\neq$ Invariance: Function and Concept Vectors in LLMs","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2510.26784","title":"LLMs Process Lists With General Filter Heads","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2511.04638","title":"Addressing divergent representations from causal interventions on neural networks","created":"2025-11-06","cited_by_count":7,"area":"mechinterp"},{"id":"2510.13796","title":"The Mechanistic Emergence of Symbol Grounding in Language Models","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2511.11579","title":"Decoupling Positional and Symbolic Attention Behavior in Transformers","created":"2025-10-03","cited_by_count":6,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2408.12664","title":"Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2505.22200","title":"Investigating Mechanisms for In-Context Vision Language Binding","created":"2025-05-28","cited_by_count":5,"area":"mllm"},{"id":"2506.04461","title":"Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2512.16902","title":"In-Context Algebra","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2604.19052","title":"Cell-Based Representation of Relational Binding in Language Models","created":"2026-04-21","cited_by_count":5,"area":null},{"id":"2504.01137","title":"Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2509.24072","title":"Uncovering Grounding IDs: How External Cues Shape Multimodal Binding","created":"2025-09-28","cited_by_count":4,"area":"mllm"},{"id":"2602.15183","title":"Seeing to Generalize: How Visual Data Corrects Binding Shortcuts","created":"2026-02-16","cited_by_count":4,"area":"mllm"},{"id":"2603.22278","title":"The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models","created":"2026-03-23","cited_by_count":4,"area":"mllm"},{"id":"2509.17514","title":"Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data","created":"2025-09-22","cited_by_count":3,"area":"ssm"},{"id":"2602.04752","title":"Decomposing Query-Key Feature Interactions Using Contrastive Covariances","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2604.15180","title":"AdaSplash-2: Faster Differentiable Sparse Attention","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2606.08644","title":"A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models","created":"2026-06-07","cited_by_count":3,"area":"mechinterp"},{"id":"2410.03203","title":"Learning Semantic Structure through First-Order-Logic Translation","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2605.09129","title":"Data-driven Circuit Discovery for Interpretability of Language Models","created":"2026-05-09","cited_by_count":2,"area":"mechinterp"},{"id":"2605.14125","title":"Polar probe linearly decodes semantic structures from LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2607.04926","title":"Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2410.08069","title":"Unlearning-based Neural Interpretations","created":"2024-10-10","cited_by_count":1,"area":"safety"},{"id":"2601.17869","title":"On the Emergence and Test-Time Use of Structural Information in Large Language Models","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2604.09942","title":"I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.21139","title":"Slot Machines: How LLMs Keep Track of Multiple Entities","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.04330","title":"The Scaling Properties of Implicit Deductive Reasoning in Transformers","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2606.04474","title":"Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2608.04183","title":"Test, then Route: How Language Models Execute In-Context Conditional Rules Across Models and Languages","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2609.11216","title":"Legible Failures: Detecting and Repairing In-Context Binding Errors","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2609.31193","title":"Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs","created":"2026-09-25","cited_by_count":1,"area":"lr"},{"id":"2502.15090","title":"ExpertLens: Activation steering features are highly interpretable","created":"2025-02-20","cited_by_count":0,"area":"mechinterp"},{"id":"2509.25002","title":"Circuit Distillation","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.19410","title":"ToMMeR -- Efficient Entity Mention Detection from Large Language Models","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2601.03914","title":"When Models Decide and When They Bind: A Two-Stage Computation for Multiple-Choice Question-Answering","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2602.07794","title":"Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2602.08548","title":"How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.10881","title":"Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.22038","title":"Source-Modality Monitoring in Vision-Language Models","created":"2026-04-23","cited_by_count":0,"area":"mllm"},{"id":"2605.07127","title":"The Position Curse: LLMs Struggle to Locate the Last Few Items in a List","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.28543","title":"Cultural Binding Heads in Language Models","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.29634","title":"Relational Rank Geometry in Transformers: Detecting and Steering Hidden-State Relation Frames","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.31503","title":"How can embedding models bind concepts?","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.11945","title":"Belief-reality separation lives in routing over a shared value slot in language models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.26179","title":"Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.00035","title":"Linguistic Context Recodes Visual Representations in Vision-Language Models","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2608.07852","title":"\"Many Are My Names\": The Anatomy of the Assistant and Its Personas via Sparse Autoencoders","created":"2026-08-08","cited_by_count":0,"area":"mechinterp"},{"id":"2608.12333","title":"Vision-Language Models are Fragile Multilingual Associators","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2608.24842","title":"Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.29189","title":"Rate-Coding Bundle Memory: A Unified Model of Memory and Control for Symbolic Computation in the Brain","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.24635","title":"Written as a Record, Read as an Address: What a Forward Pass Leaves in an Operation's KV Cache","created":"2026-09-21","cited_by_count":0,"area":"inference"},{"id":"2609.30634","title":"In-Context Binding Capacity in Language Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.31401","title":"Decodable In-Context State and Model Output Across Training","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32942","title":"The Key Handoff: Retrieval in Hybrid Language Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33883","title":"Lost with a Map: Conversational State and Behavioral Reliability in Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35663","title":"Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35970","title":"Causal and Interpretable Structures in LLM Compositional Tasks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36585","title":"Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":"100"}