{"total":132,"rows":[{"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,"area":"mechinterp"},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001,"area":null},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623,"area":"mechinterp"},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359,"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":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236,"area":"diffusion"},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235,"area":"mechinterp"},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161,"area":null},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"area":null},{"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":"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":"2409.10695","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97,"area":"lr"},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2303.09435","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","created":"2023-03-16","cited_by_count":90,"area":null},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"area":null},{"id":"2309.15098","title":"Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models","created":"2023-09-26","cited_by_count":67,"area":null},{"id":"2411.18620","title":"Cross-modal Information Flow in Multimodal Large Language Models","created":"2024-11-27","cited_by_count":67,"area":"mllm"},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2402.09221","title":"Spectral Filters, Dark Signals, and Attention Sinks","created":"2024-02-14","cited_by_count":56,"area":"mechinterp"},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"id":"2410.05864","title":"From Tokens to Words: On the Inner Lexicon of LLMs","created":"2024-10-08","cited_by_count":48,"area":null},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2403.01548","title":"In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation","created":"2024-03-03","cited_by_count":45,"area":null},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"area":null},{"id":"2410.06331","title":"Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing","created":"2024-10-08","cited_by_count":37,"area":null},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"area":null},{"id":"2310.19704","title":"A Survey on Knowledge Editing of Neural Networks","created":"2023-10-30","cited_by_count":34,"area":null},{"id":"2404.13400","title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","created":"2024-04-20","cited_by_count":31,"area":null},{"id":"2405.20612","title":"UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation","created":"2024-05-31","cited_by_count":31,"area":null},{"id":"2406.11614","title":"Intrinsic Test of Unlearning Using Parametric Knowledge Traces","created":"2024-06-17","cited_by_count":29,"area":"safety"},{"id":"2502.01615","title":"Large Language Models Are Human-Like Internally","created":"2025-02-03","cited_by_count":29,"area":"mechinterp"},{"id":"2212.10380","title":"What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2310.18969","title":"Analyzing Vision Transformers for Image Classification in Class Embedding Space","created":"2023-10-29","cited_by_count":26,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2302.12461","title":"Analyzing And Editing Inner Mechanisms Of Backdoored Language Models","created":"2023-02-24","cited_by_count":23,"area":"safety"},{"id":"2308.12462","title":"Overcoming Generic Knowledge Loss with Selective Parameter Update","created":"2023-08-23","cited_by_count":23,"area":null},{"id":"2502.10835","title":"Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models","created":"2025-02-15","cited_by_count":23,"area":"lr"},{"id":"2310.03686","title":"DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers","created":"2023-10-05","cited_by_count":22,"area":null},{"id":"2310.16270","title":"Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism","created":"2023-10-25","cited_by_count":22,"area":null},{"id":"2309.05605","title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models","created":"2023-09-11","cited_by_count":21,"area":"lr"},{"id":"2406.12288","title":"An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs","created":"2024-06-18","cited_by_count":20,"area":"lr"},{"id":"2510.17205","title":"$\\mathcal{V}isi\\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs","created":"2025-10-20","cited_by_count":17,"area":"mllm"},{"id":"2510.21518","title":"Head Pursuit: Probing Attention Specialization in Multimodal Transformers","created":"2025-10-24","cited_by_count":17,"area":"mllm"},{"id":"2404.07004","title":"LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models","created":"2024-04-10","cited_by_count":16,"area":null},{"id":"2511.06876","title":"Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions","created":"2025-11-10","cited_by_count":14,"area":null},{"id":"2406.09325","title":"REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space","created":"2024-06-13","cited_by_count":13,"area":"safety"},{"id":"2312.01648","title":"Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2405.14880","title":"Dissecting Query-Key Interaction in Vision Transformers","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2310.07325","title":"An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L","created":"2023-10-11","cited_by_count":11,"area":null},{"id":"2405.18432","title":"Unsupervised Model Tree Heritage Recovery","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2411.10950","title":"Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering","created":"2024-11-17","cited_by_count":11,"area":"mllm"},{"id":"2405.08553","title":"Improving Transformers with Dynamically Composable Multi-Head Attention","created":"2024-05-14","cited_by_count":10,"area":null},{"id":"2407.11540","title":"Not Another Imputation Method: A Transformer-based Model for Missing Values in Tabular Datasets","created":"2024-07-16","cited_by_count":10,"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":"2506.06231","title":"Towards an Explainable Comparison and Alignment of Feature Embeddings","created":"2025-06-06","cited_by_count":10,"area":null},{"id":"2506.08210","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation","created":"2025-06-09","cited_by_count":10,"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":"2505.16538","title":"Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2309.07315","title":"Traveling Words: A Geometric Interpretation of Transformers","created":"2023-09-13","cited_by_count":7,"area":null},{"id":"2405.17653","title":"InversionView: A General-Purpose Method for Reading Information from Neural Activations","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2505.18832","title":"Localizing Knowledge in Diffusion Transformers","created":"2025-05-24","cited_by_count":7,"area":"diffusion"},{"id":"2510.04933","title":"The Geometry of Truth: Layer-wise Semantic Dynamics for Hallucination Detection in Large Language Models","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2602.04428","title":"Fine-Grained Activation Steering: Steering Less, Achieving More","created":"2026-02-04","cited_by_count":7,"area":"mechinterp"},{"id":"2604.15574","title":"Why Fine-Tuning Encourages Hallucinations and How to Fix It","created":"2026-04-16","cited_by_count":7,"area":"distill"},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2502.10871","title":"Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs","created":"2025-02-15","cited_by_count":6,"area":null},{"id":"2604.02608","title":"Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens","created":"2026-04-03","cited_by_count":6,"area":"mechinterp"},{"id":"2406.13185","title":"LIVE: Learnable In-Context Vector for Visual Question Answering","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2407.06162","title":"RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model","created":"2024-06-02","cited_by_count":5,"area":null},{"id":"2502.14133","title":"Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification","created":"2025-02-19","cited_by_count":5,"area":"mechinterp"},{"id":"2504.15471","title":"Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2512.16902","title":"In-Context Algebra","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2602.00398","title":"MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2411.17182","title":"An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2505.13515","title":"LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades","created":"2025-05-17","cited_by_count":4,"area":null},{"id":"2507.00322","title":"Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2510.02348","title":"mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2510.02524","title":"Unraveling Syntax: Language Modeling and the Substructure of Grammars","created":"2025-10-02","cited_by_count":4,"area":null},{"id":"2606.03280","title":"A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting","created":"2026-06-02","cited_by_count":4,"area":null},{"id":"2406.02721","title":"Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2504.16871","title":"Exploring How LLMs Capture and Represent Domain-Specific Knowledge","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2510.04108","title":"Can Linear Probes Measure LLM Uncertainty?","created":"2025-10-05","cited_by_count":3,"area":"mechinterp"},{"id":"2510.21834","title":"Restoring Pruned Large Language Models via Lost Component Compensation","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2604.06005","title":"Disentangling MLP Neuron Weights in Vocabulary Space","created":"2026-04-07","cited_by_count":3,"area":"mechinterp"},{"id":"2607.04319","title":"Legible-by-Construction: Attention and End-to-End Transformers","created":"2026-07-05","cited_by_count":3,"area":null},{"id":"2310.06977","title":"Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2406.02060","title":"I've got the \"Answer\"! Interpretation of LLMs Hidden States in Question Answering","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2502.11646","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2502.13490","title":"What are Models Thinking about? Understanding Large Language Model Hallucinations \"Psychology\" through Model Inner State Analysis","created":"2025-02-19","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}