{"list":"other","total":72,"rows":[{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2410.10762","title":"AFlow: Automating Agentic Workflow Generation","created":"2024-10-14","cited_by_count":432},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2502.18864","title":"Accelerating scientific discovery with Co-Scientist","created":"2025-02-26","cited_by_count":401},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"1802.03888","title":"Consistent Individualized Feature Attribution for Tree Ensembles","created":"2018-02-12","cited_by_count":285},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2205.01833","title":"OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts","created":"2022-05-04","cited_by_count":177},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160},{"id":"2606.15497","title":"Towards End-to-End Automation of AI Research","created":"2026-03-31","cited_by_count":159},{"id":"2403.17806","title":"Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms","created":"2024-03-26","cited_by_count":149},{"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":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126},{"id":"2107.07436","title":"FastSHAP: Real-Time Shapley Value Estimation","created":"2021-07-15","cited_by_count":125},{"id":"2502.02533","title":"Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies","created":"2025-02-04","cited_by_count":113},{"id":"2402.03620","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","created":"2024-02-06","cited_by_count":110},{"id":"2501.05707","title":"Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains","created":"2025-01-10","cited_by_count":95},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91},{"id":"2504.15228","title":"A Self-Improving Coding Agent","created":"2025-04-21","cited_by_count":79},{"id":"2505.20063","title":"SAEs Are Good for Steering -- If You Select the Right Features","created":"2025-05-26","cited_by_count":78},{"id":"2412.12101","title":"InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders","created":"2024-11-13","cited_by_count":66},{"id":"2506.16499","title":"ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning","created":"2025-06-19","cited_by_count":61},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47},{"id":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43},{"id":"2510.05024","title":"Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment","created":"2025-10-06","cited_by_count":43},{"id":"2604.02029","title":"The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook","created":"2026-04-02","cited_by_count":43},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34},{"id":"2509.23886","title":"Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer","created":"2025-09-28","cited_by_count":34},{"id":"2410.23743","title":"What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective","created":"2024-10-31","cited_by_count":29},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29},{"id":"2305.19911","title":"Neuron to Graph: Interpreting Language Model Neurons at Scale","created":"2023-05-31","cited_by_count":27},{"id":"2211.10590","title":"Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model","created":"2022-11-19","cited_by_count":25},{"id":"2212.13881","title":"Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features","created":"2022-12-28","cited_by_count":25},{"id":"2410.14182","title":"LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs","created":"2024-10-18","cited_by_count":25},{"id":"2503.11667","title":"LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models","created":"2025-02-24","cited_by_count":23},{"id":"2402.14700","title":"Unveiling Linguistic Regions in Large Language Models","created":"2024-02-22","cited_by_count":22},{"id":"2309.00570","title":"Mechanism of feature learning in convolutional neural networks","created":"2023-09-01","cited_by_count":17},{"id":"2604.25891","title":"Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers","created":"2026-04-28","cited_by_count":17},{"id":"2408.05859","title":"The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms","created":"2024-08-11","cited_by_count":13},{"id":"2508.21258","title":"RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching","created":"2025-08-28","cited_by_count":13},{"id":"2606.00995","title":"Subliminal Learning Is Steering Vector Distillation","created":"2026-05-31","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":"2405.04912","title":"GP-MoLFormer: A Foundation Model For Molecular Generation","created":"2024-04-04","cited_by_count":11},{"id":"2511.20820","title":"SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models","created":"2025-11-25","cited_by_count":10},{"id":"2605.12671","title":"All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs","created":"2026-05-12","cited_by_count":9},{"id":"2603.09517","title":"You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases","created":"2026-03-10","cited_by_count":8},{"id":"2606.26448","title":"Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist","created":"2026-06-24","cited_by_count":8},{"id":"2605.23645","title":"Learning Through Noise: Why Subliminal Learning Works and When It Fails","created":"2026-05-22","cited_by_count":7},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7},{"id":"2606.00831","title":"Subliminal Learning is a LoRA Artifact","created":"2026-05-30","cited_by_count":6},{"id":"2603.03415","title":"Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs","created":"2026-03-03","cited_by_count":4},{"id":"2605.01555","title":"Automated Interpretability and Feature Discovery in Language Models with Agents","created":"2026-05-02","cited_by_count":4},{"id":"2606.11722","title":"ICA Lens: Interpreting Language Models Without Training Another Dictionary","created":"2026-06-10","cited_by_count":4},{"id":"2605.22878","title":"SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research","created":"2026-05-20","cited_by_count":1}],"next_cursor":null}