{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"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":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"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},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"1807.01251","title":"Training behavior of deep neural network in frequency domain","created":"2018-07-03","cited_by_count":174},{"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":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102},{"id":"1909.11304","title":"Asymptotics of Wide Networks from Feynman Diagrams","created":"2019-09-25","cited_by_count":77},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72},{"id":"2105.03703","title":"Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics","created":"2021-05-08","cited_by_count":57},{"id":"2308.12108","title":"The Local Learning Coefficient: A Singularity-Aware Complexity Measure","created":"2023-08-23","cited_by_count":51},{"id":"2009.10685","title":"Tensor Programs III: Neural Matrix Laws","created":"2020-09-22","cited_by_count":49},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36},{"id":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34},{"id":"2404.14994","title":"Transformers Can Represent $n$-gram Language Models","created":"2024-04-23","cited_by_count":32},{"id":"2402.04362","title":"Neural Networks Learn Statistics of Increasing Complexity","created":"2024-02-06","cited_by_count":31},{"id":"2410.06672","title":"Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures","created":"2024-10-09","cited_by_count":31},{"id":"2407.12034","title":"Understanding Transformers via N-gram Statistics","created":"2024-06-30","cited_by_count":26},{"id":"2009.09435","title":"Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation","created":"2020-09-20","cited_by_count":25},{"id":"2405.13868","title":"Automatically Identifying Local and Global Circuits with Linear Computation Graphs","created":"2024-05-22","cited_by_count":24},{"id":"1707.04848","title":"Do Neural Nets Learn Statistical Laws behind Natural Language?","created":"2017-07-16","cited_by_count":16},{"id":"2402.03698","title":"Estimating the Local Learning Coefficient at Scale","created":"2024-02-06","cited_by_count":6},{"id":"2410.06024","title":"Jet Expansions of Residual Computation","created":"2024-10-08","cited_by_count":4},{"id":"2505.13900","title":"New Evidence of the Two-Phase Learning Dynamics of Neural Networks","created":"2025-05-20","cited_by_count":3}],"next_cursor":null}