{"list":"other","total":63,"rows":[{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"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":"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":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"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":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308},{"id":"2007.06346","title":"Whitening for Self-Supervised Representation Learning","created":"2020-07-13","cited_by_count":279},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"2012.13635","title":"Logic Tensor Networks","created":"2020-12-25","cited_by_count":199},{"id":"2605.29358","title":"Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet","created":"2026-05-28","cited_by_count":191},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132},{"id":"2311.04897","title":"Future Lens: Anticipating Subsequent Tokens from a Single Hidden State","created":"2023-11-08","cited_by_count":121},{"id":"2006.13155","title":"Logical Neural Networks","created":"2020-06-23","cited_by_count":119},{"id":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113},{"id":"2002.06100","title":"Analyzing Differentiable Fuzzy Logic Operators","created":"2020-02-14","cited_by_count":101},{"id":"1710.04773","title":"Residual Connections Encourage Iterative Inference","created":"2017-10-13","cited_by_count":77},{"id":"2405.12241","title":"Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning","created":"2024-05-17","cited_by_count":67},{"id":"1612.07771","title":"Highway and Residual Networks learn Unrolled Iterative Estimation","created":"2016-12-22","cited_by_count":52},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48},{"id":"2410.14670","title":"Decomposing The Dark Matter of Sparse Autoencoders","created":"2024-10-18","cited_by_count":45},{"id":"2408.05451","title":"Mathematical Models of Computation in Superposition","created":"2024-08-10","cited_by_count":35},{"id":"2211.12312","title":"Interpreting Neural Networks through the Polytope Lens","created":"2022-11-22","cited_by_count":33},{"id":"2410.08417","title":"Bilinear MLPs enable weight-based mechanistic interpretability","created":"2024-10-10","cited_by_count":28},{"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},{"id":"2305.16765","title":"Backpack Language Models","created":"2023-05-26","cited_by_count":15},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10},{"id":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10},{"id":"2510.12269","title":"Tensor Logic: The Language of AI","created":"2025-10-14","cited_by_count":8},{"id":"2604.02608","title":"Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens","created":"2026-04-03","cited_by_count":6},{"id":"2302.09458","title":"Learning Language Representations with Logical Inductive Bias","created":"2023-02-19","cited_by_count":5},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5},{"id":"2606.31845","title":"Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors","created":"2026-06-30","cited_by_count":3},{"id":"2607.04319","title":"Legible-by-Construction: Attention and End-to-End Transformers","created":"2026-07-05","cited_by_count":3},{"id":"2508.08172","title":"Neural Logic Networks for Interpretable Classification","created":"2025-08-11","cited_by_count":2},{"id":"2604.10604","title":"NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings","created":"2026-04-12","cited_by_count":1}],"next_cursor":null}