{"list":"other","total":62,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"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":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"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":"2106.04619","title":"Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style","created":"2021-06-08","cited_by_count":312},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"1805.08651","title":"Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning","created":"2018-05-22","cited_by_count":282},{"id":"1605.06336","title":"Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA","created":"2016-05-20","cited_by_count":273},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"id":"2501.16496","title":"Open Problems in Mechanistic Interpretability","created":"2025-01-27","cited_by_count":179},{"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":"2209.11924","title":"Interventional Causal Representation Learning","created":"2022-09-24","cited_by_count":142},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115},{"id":"2306.00542","title":"Nonparametric Identifiability of Causal Representations from Unknown Interventions","created":"2023-06-01","cited_by_count":106},{"id":"2007.00810","title":"On Linear Identifiability of Learned Representations","created":"2020-07-01","cited_by_count":105},{"id":"2306.02235","title":"Learning Linear Causal Representations from Interventions under General Nonlinear Mixing","created":"2023-06-04","cited_by_count":92},{"id":"2211.16467","title":"Linear Causal Disentanglement via Interventions","created":"2022-11-29","cited_by_count":84},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79},{"id":"2010.02637","title":"Weakly Supervised Disentangled Generative Causal Representation Learning","created":"2020-10-06","cited_by_count":68},{"id":"2405.12241","title":"Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning","created":"2024-05-17","cited_by_count":67},{"id":"2106.15563","title":"Learning latent causal graphs via mixture oracles","created":"2021-06-29","cited_by_count":55},{"id":"2408.00113","title":"Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models","created":"2024-07-31","cited_by_count":51},{"id":"2301.08230","title":"Score-based Causal Representation Learning with Interventions","created":"2023-01-19","cited_by_count":49},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","cited_by_count":38},{"id":"1503.00778","title":"Simple, Efficient, and Neural Algorithms for Sparse Coding","created":"2015-03-02","cited_by_count":37},{"id":"2208.14153","title":"Identifying Weight-Variant Latent Causal Models","created":"2022-08-30","cited_by_count":34},{"id":"2402.09236","title":"Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models","created":"2024-02-14","cited_by_count":29},{"id":"2211.12270","title":"Causal Abstraction with Soft Interventions","created":"2022-11-22","cited_by_count":23},{"id":"2310.15580","title":"Identifiable Latent Polynomial Causal Models Through the Lens of Change","created":"2023-10-24","cited_by_count":23},{"id":"2406.00519","title":"Learning Discrete Concepts in Latent Hierarchical Models","created":"2024-06-01","cited_by_count":17},{"id":"2101.10373","title":"Bayesian Pyramids: Identifiable Multilayer Discrete Latent Structure Models for Discrete Data","created":"2021-01-25","cited_by_count":16},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14},{"id":"2402.15309","title":"Counterfactual Generation with Identifiability Guarantees","created":"2024-02-23","cited_by_count":13},{"id":"2208.14161","title":"Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation","created":"2022-08-30","cited_by_count":12},{"id":"2006.06226","title":"Discrete Latent Variable Representations for Low-Resource Text Classification","created":"2020-06-11","cited_by_count":10},{"id":"2402.06223","title":"Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning","created":"2024-02-09","cited_by_count":10},{"id":"2305.18657","title":"Representation Of Lexical Stylistic Features In Language Models' Embedding Space","created":"2023-05-29","cited_by_count":8},{"id":"2408.10234","title":"The Unbearable Slowness of Being: Why do we live at 10 bits/s?","created":"2024-08-03","cited_by_count":8},{"id":"2502.09297","title":"When Do Neural Networks Learn World Models?","created":"2025-02-13","cited_by_count":8},{"id":"2403.15711","title":"Towards Identifiable Latent Additive Noise Models","created":"2024-03-23","cited_by_count":5}],"next_cursor":null}