{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143},{"id":"2006.12433","title":"What shapes feature representations? Exploring datasets, architectures, and training","created":"2020-06-22","cited_by_count":126},{"id":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108},{"id":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105},{"id":"2305.08809","title":"Interpretability at Scale: Identifying Causal Mechanisms in Alpaca","created":"2023-05-15","cited_by_count":103},{"id":"1905.12506","title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","created":"2019-05-29","cited_by_count":100},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97},{"id":"2006.07886","title":"On Disentangled Representations Learned From Correlated Data","created":"2020-06-14","cited_by_count":94},{"id":"1809.10374","title":"An analytic theory of generalization dynamics and transfer learning in deep linear networks","created":"2018-09-27","cited_by_count":85},{"id":"2001.03632","title":"Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks","created":"2020-01-10","cited_by_count":72},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65},{"id":"2010.07515","title":"RNNs can generate bounded hierarchical languages with optimal memory","created":"2020-10-15","cited_by_count":59},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59},{"id":"2305.18741","title":"Grokking of Hierarchical Structure in Vanilla Transformers","created":"2023-05-30","cited_by_count":53},{"id":"2006.11098","title":"Mechanisms for Handling Nested Dependencies in Neural-Network Language Models and Humans","created":"2020-06-19","cited_by_count":42},{"id":"2306.04507","title":"Improving neural network representations using human similarity judgments","created":"2023-06-07","cited_by_count":38},{"id":"2310.02541","title":"Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data","created":"2023-10-04","cited_by_count":33},{"id":"2305.16536","title":"Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression","created":"2023-05-25","cited_by_count":30},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19},{"id":"1809.06848","title":"On the Learning Dynamics of Deep Neural Networks","created":"2018-09-18","cited_by_count":18},{"id":"2311.09466","title":"Soft Matching Distance: A metric on neural representations that captures single-neuron tuning","created":"2023-11-16","cited_by_count":18},{"id":"2403.03375","title":"Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations","created":"2024-03-05","cited_by_count":12},{"id":"2310.17074","title":"Benign Oscillation of Stochastic Gradient Descent with Large Learning Rates","created":"2023-10-26","cited_by_count":8},{"id":"2401.13558","title":"Task structure and nonlinearity jointly determine learned representational geometry","created":"2024-01-24","cited_by_count":6}],"next_cursor":null}