{"list":"other","total":85,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"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":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"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":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160},{"id":"1611.00740","title":"Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review","created":"2016-11-02","cited_by_count":155},{"id":"1910.12478","title":"Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes","created":"2019-10-28","cited_by_count":151},{"id":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143},{"id":"2503.17547","title":"Learning Multi-Level Features with Matryoshka Sparse Autoencoders","created":"2025-03-21","cited_by_count":143},{"id":"2503.09532","title":"SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability","created":"2025-03-12","cited_by_count":124},{"id":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113},{"id":"2402.01092","title":"A Dynamical Model of Neural Scaling Laws","created":"2024-02-02","cited_by_count":111},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108},{"id":"2205.09653","title":"Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks","created":"2022-05-19","cited_by_count":105},{"id":"1608.08225","title":"Why does deep and cheap learning work so well?","created":"2016-08-29","cited_by_count":100},{"id":"2101.08515","title":"Pre-training without Natural Images","created":"2021-01-21","cited_by_count":100},{"id":"2402.16991","title":"A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data","created":"2024-02-26","cited_by_count":93},{"id":"2501.16615","title":"Sparse Autoencoders Trained on the Same Data Learn Different Features","created":"2025-01-28","cited_by_count":93},{"id":"2106.05963","title":"Learning to See by Looking at Noise","created":"2021-06-10","cited_by_count":92},{"id":"2107.04384","title":"Continual Learning in the Teacher-Student Setup: Impact of Task Similarity","created":"2021-07-09","cited_by_count":88},{"id":"2502.04878","title":"Sparse Autoencoders Do Not Find Canonical Units of Analysis","created":"2025-02-07","cited_by_count":88},{"id":"2307.02129","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","created":"2023-07-05","cited_by_count":71},{"id":"2108.10573","title":"The staircase property: How hierarchical structure can guide deep learning","created":"2021-08-24","cited_by_count":62},{"id":"2008.08601","title":"Neural Networks and Quantum Field Theory","created":"2020-08-19","cited_by_count":61},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61},{"id":"1410.3831","title":"An exact mapping between the Variational Renormalization Group and Deep Learning","created":"2014-10-14","cited_by_count":56},{"id":"2409.14623","title":"From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks","created":"2024-09-22","cited_by_count":49},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49},{"id":"2310.03789","title":"Grokking as a First Order Phase Transition in Two Layer Networks","created":"2023-10-05","cited_by_count":48},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47},{"id":"2410.14670","title":"Decomposing The Dark Matter of Sparse Autoencoders","created":"2024-10-18","cited_by_count":45},{"id":"2304.03408","title":"Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks","created":"2023-04-06","cited_by_count":43},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42},{"id":"2402.02364","title":"Loss Landscape Degeneracy and Stagewise Development in Transformers","created":"2024-02-04","cited_by_count":40},{"id":"2306.04251","title":"Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks","created":"2023-06-07","cited_by_count":39},{"id":"2406.00048","title":"Towards a theory of how the structure of language is acquired by deep neural networks","created":"2024-05-28","cited_by_count":39},{"id":"1808.07593","title":"Caveats for information bottleneck in deterministic scenarios","created":"2018-08-23","cited_by_count":34},{"id":"1704.06279","title":"Mutual Information, Neural Networks and the Renormalization Group","created":"2017-04-20","cited_by_count":33},{"id":"2106.04110","title":"A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs","created":"2021-06-08","cited_by_count":33},{"id":"1902.11239","title":"Quantifying High-order Interdependencies via Multivariate Extensions of the Mutual Information","created":"2019-02-28","cited_by_count":30},{"id":"2408.12578","title":"A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language","created":"2024-08-22","cited_by_count":26},{"id":"2410.13770","title":"Probing the Latent Hierarchical Structure of Data via Diffusion Models","created":"2024-10-17","cited_by_count":26},{"id":"1612.09057","title":"Deep Learning and Hierarchal Generative Models","created":"2016-12-29","cited_by_count":25},{"id":"1903.03488","title":"Is Deeper Better only when Shallow is Good?","created":"2019-03-08","cited_by_count":24},{"id":"2109.13247","title":"The edge of chaos: quantum field theory and deep neural networks","created":"2021-09-27","cited_by_count":24},{"id":"2410.17770","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","created":"2024-10-23","cited_by_count":21},{"id":"1803.09522","title":"A Provably Correct Algorithm for Deep Learning that Actually Works","created":"2018-03-26","cited_by_count":20},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18},{"id":"2505.07067","title":"Learning curves theory for hierarchically compositional data with power-law distributed features","created":"2025-05-11","cited_by_count":17},{"id":"2410.13211","title":"Estimating the Probabilities of Rare Outputs in Language Models","created":"2024-10-17","cited_by_count":16},{"id":"2412.07942","title":"Neural Scaling Laws Rooted in the Data Distribution","created":"2024-12-10","cited_by_count":15},{"id":"1405.6664","title":"On the Computational Intractability of Exact and Approximate Dictionary Learning","created":"2014-05-26","cited_by_count":14},{"id":"2305.10491","title":"Bayesian Renormalization","created":"2023-05-17","cited_by_count":14},{"id":"2408.00677","title":"Scaling Backwards: Minimal Synthetic Pre-training?","created":"2024-08-01","cited_by_count":14},{"id":"2506.06489","title":"Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks","created":"2025-06-06","cited_by_count":14},{"id":"2507.02550","title":"Position: A Theory of Deep Learning Must Include Compositional Sparsity","created":"2025-07-03","cited_by_count":14},{"id":"2509.26544","title":"Bayesian Influence Functions for Hessian-Free Data Attribution","created":"2025-09-30","cited_by_count":14},{"id":"2504.18274","title":"Structural Inference: Interpreting Small Language Models with Susceptibilities","created":"2025-04-25","cited_by_count":13},{"id":"2501.16241","title":"Phase Transitions in Large Language Models and the $O(N)$ Model","created":"2025-01-27","cited_by_count":12},{"id":"2505.03439","title":"The Steganographic Potentials of Language Models","created":"2025-05-06","cited_by_count":10},{"id":"2405.17538","title":"Bayesian RG Flow in Neural Network Field Theories","created":"2024-05-27","cited_by_count":9},{"id":"2509.26537","title":"The Loss Kernel: A Geometric Probe for Deep Learning Interpretability","created":"2025-09-30","cited_by_count":9},{"id":"2211.06738","title":"Formalizing the presumption of independence","created":"2022-11-12","cited_by_count":8},{"id":"2402.00944","title":"NCoder -- A Quantum Field Theory approach to encoding data","created":"2024-02-01","cited_by_count":8},{"id":"2405.06008","title":"Wilsonian Renormalization of Neural Network Gaussian Processes","created":"2024-05-09","cited_by_count":8},{"id":"2312.06608","title":"Information theory for dimensionality reduction in dynamical systems","created":"2023-12-11","cited_by_count":4},{"id":"2510.00468","title":"Feature Identification via the Empirical NTK","created":"2025-10-01","cited_by_count":4},{"id":"2512.04165","title":"Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity","created":"2025-12-03","cited_by_count":4},{"id":"1609.03541","title":"Comment on \"Why does deep and cheap learning work so well?\" [arXiv:1608.08225]","created":"2016-09-12","cited_by_count":3},{"id":"1706.03149","title":"An Expectation-Maximization Algorithm for the Fractal Inverse Problem","created":"2017-06-09","cited_by_count":3},{"id":"2502.01739","title":"Grokking vs. Learning: Same Features, Different Encodings","created":"2025-02-03","cited_by_count":2},{"id":"2504.20197","title":"Representation Learning on a Random Lattice","created":"2025-04-28","cited_by_count":2},{"id":"2601.03368","title":"A path to natural language through tokenisation and transformers","created":"2026-01-06","cited_by_count":2},{"id":"2512.00984","title":"Symmetries at the origin of hierarchical emergence","created":"2025-11-30","cited_by_count":1}],"next_cursor":null}