{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"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},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196},{"id":"2501.16496","title":"Open Problems in Mechanistic Interpretability","created":"2025-01-27","cited_by_count":179},{"id":"1710.11379","title":"Latent Space Oddity: on the Curvature of Deep Generative Models","created":"2017-10-31","cited_by_count":174},{"id":"1601.03764","title":"Linear Algebraic Structure of Word Senses, with Applications to Polysemy","created":"2016-01-14","cited_by_count":165},{"id":"2310.15154","title":"Linear Representations of Sentiment in Large Language Models","created":"2023-10-23","cited_by_count":163},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142},{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101},{"id":"1711.08014","title":"The Riemannian Geometry of Deep Generative Models","created":"2017-11-21","cited_by_count":82},{"id":"2311.17030","title":"Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching","created":"2023-11-28","cited_by_count":80},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79},{"id":"1808.08271","title":"An elementary introduction to information geometry","created":"2018-08-17","cited_by_count":76},{"id":"2507.22062","title":"Meta CLIP 2: A Worldwide Scaling Recipe","created":"2025-07-29","cited_by_count":64},{"id":"2407.10264","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","created":"2024-07-14","cited_by_count":55},{"id":"2505.18235","title":"The Origins of Representation Manifolds in Large Language Models","created":"2025-05-23","cited_by_count":51},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46},{"id":"2008.00565","title":"Geometrically Enriched Latent Spaces","created":"2020-08-02","cited_by_count":45},{"id":"2406.04341","title":"Interpreting the Second-Order Effects of Neurons in CLIP","created":"2024-06-06","cited_by_count":36},{"id":"2410.17245","title":"Towards Reliable Evaluation of Behavior Steering Interventions in LLMs","created":"2024-10-22","cited_by_count":36},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33},{"id":"2009.09435","title":"Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation","created":"2020-09-20","cited_by_count":25},{"id":"2106.05367","title":"Pulling back information geometry","created":"2021-06-09","cited_by_count":23},{"id":"2504.01002","title":"Token embeddings violate the manifold hypothesis","created":"2025-04-01","cited_by_count":16},{"id":"2410.08993","title":"The structure of the token space for large language models","created":"2024-10-11","cited_by_count":10},{"id":"2502.11447","title":"Does Editing Provide Evidence for Localization?","created":"2025-02-17","cited_by_count":7},{"id":"2510.16820","title":"Finding Manifolds With Bilinear Autoencoders","created":"2025-10-19","cited_by_count":5},{"id":"1912.02280","title":"Natural Alpha Embeddings","created":"2019-12-04","cited_by_count":4},{"id":"2506.01599","title":"Connecting Neural Models Latent Geometries with Relative Geodesic Representations","created":"2025-06-02","cited_by_count":4}],"next_cursor":null}