A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks

21 March 2023

Papers citing "A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks"

40 / 40 papers shown

Title
How Do Transformers Learn Variable Binding in Symbolic Programs? Yiwei Wu Atticus Geiger Raphaël Millière NAI 41 1 0 27 May 2025
Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model Zhiwei Xu Zhiyu Ni Yixin Wang Wei Hu CLL 105 2 0 17 Apr 2025
Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases Michael Y. Hu Jackson Petty Chuan Shi William Merrill Tal Linzen AI4CE 135 2 0 26 Feb 2025
Mechanistic? Naomi Saphra Sarah Wiegreffe AI4CE 75 13 0 07 Oct 2024
Grokking at the Edge of Linear Separability Alon Beck Noam Levi Yohai Bar-Sinai 80 1 0 06 Oct 2024
Approaching Deep Learning through the Spectral Dynamics of Weights David Yunis Kumar Kshitij Patel Samuel Wheeler Pedro H. P. Savarese Gal Vardi Karen Livescu Michael Maire Matthew R. Walter 112 3 0 21 Aug 2024
Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition Kenzo Clauw S. Stramaglia Daniele Marinazzo 84 4 0 16 Aug 2024
Knowledge Mechanisms in Large Language Models: A Survey and Perspective Meng Wang Yunzhi Yao Ziwen Xu Shuofei Qiao Shumin Deng ... Yong Jiang Pengjun Xie Fei Huang Huajun Chen Ningyu Zhang 141 39 0 22 Jul 2024
Grokking Modular Polynomials Darshil Doshi Tianyu He Aritra Das Andrey Gromov 89 5 0 05 Jun 2024
A rationale from frequency perspective for grokking in training neural network Zhangchen Zhou Yaoyu Zhang Z. Xu 88 2 0 24 May 2024
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization Boshi Wang Xiang Yue Yu-Chuan Su Huan Sun LRM 151 50 0 23 May 2024
Progress Measures for Grokking on Real-world Tasks Satvik Golechha 96 2 0 21 May 2024
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers Kabir Ahuja Vidhisha Balachandran Madhur Panwar Tianxing He Noah A. Smith Navin Goyal Yulia Tsvetkov 106 8 0 25 Apr 2024
Mechanistic Interpretability for AI Safety -- A Review Leonard Bereska E. Gavves AI4CE 137 158 0 22 Apr 2024
Eigenpruning: an Interpretability-Inspired PEFT Method Tomás Vergara-Browne Álvaro Soto A. Aizawa 86 1 0 04 Apr 2024
The Garden of Forking Paths: Observing Dynamic Parameters Distribution in Large Language Models Carlo Nicolini Jacopo Staiano Bruno Lepri Raffaele Marino MoE 62 1 0 13 Mar 2024
The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models Adithya Bhaskar Dan Friedman Danqi Chen 114 7 0 06 Mar 2024
Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations GuanWen Qiu Da Kuang Surbhi Goel 110 8 0 05 Mar 2024
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains Benjamin L. Edelman Ezra Edelman Surbhi Goel Eran Malach Nikolaos Tsilivis BDL 91 56 0 16 Feb 2024
Towards Uncovering How Large Language Model Works: An Explainability Perspective Haiyan Zhao Fan Yang Bo Shen Himabindu Lakkaraju Jundong Li 91 13 0 16 Feb 2024
Measuring Sharpness in Grokking Jack Miller Patrick Gleeson Charles OÑeill Thang Bui Noam Levi 71 1 0 14 Feb 2024
Grokking Group Multiplication with Cosets Dashiell Stander Qinan Yu Honglu Fan Stella Biderman 93 11 0 11 Dec 2023
Interpretability Illusions in the Generalization of Simplified Models Dan Friedman Andrew Kyle Lampinen Lucas Dixon Danqi Chen Asma Ghandeharioun 113 15 0 06 Dec 2023
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking Kaifeng Lyu Jikai Jin Zhiyuan Li Simon S. Du Jason D. Lee Wei Hu AI4CE 92 38 0 30 Nov 2023
Understanding Grokking Through A Robustness Viewpoint Zhiquan Tan Weiran Huang AAML OOD 64 7 0 11 Nov 2023
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization Elan Rosenfeld Andrej Risteski 90 12 0 07 Nov 2023
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks Gouki Minegishi Yusuke Iwasawa Yutaka Matsuo 65 3 0 30 Oct 2023
In-Context Learning Dynamics with Random Binary Sequences Eric J. Bigelow Ekdeep Singh Lubana Robert P. Dick Hidenori Tanaka T. Ullman 92 4 0 26 Oct 2023
Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity Jack Miller Charles OÑeill Thang Bui 77 10 0 26 Oct 2023
Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding Noam Levi Alon Beck Yohai Bar-Sinai 66 16 0 25 Oct 2023
To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets Darshil Doshi Aritra Das Tianyu He Andrey Gromov OOD 112 7 0 19 Oct 2023
Grokking as Compression: A Nonlinear Complexity Perspective Ziming Liu Ziqian Zhong Max Tegmark 65 10 0 09 Oct 2023
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data Zhiwei Xu Yutong Wang Spencer Frei Gal Vardi Wei Hu MLT 92 28 0 04 Oct 2023
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs Angelica Chen Ravid Schwartz-Ziv Kyunghyun Cho Matthew L. Leavitt Naomi Saphra 145 74 0 13 Sep 2023
Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck Benjamin L. Edelman Surbhi Goel Sham Kakade Eran Malach Cyril Zhang 91 8 0 07 Sep 2023
Explaining grokking through circuit efficiency Vikrant Varma Rohin Shah Zachary Kenton János Kramár Ramana Kumar 97 55 0 05 Sep 2023
Latent State Models of Training Dynamics Michael Y. Hu Angelica Chen Naomi Saphra Kyunghyun Cho 115 8 0 18 Aug 2023
The semantic landscape paradigm for neural networks Shreyas Gokhale 94 2 0 18 Jul 2023
Faith and Fate: Limits of Transformers on Compositionality Nouha Dziri Ximing Lu Melanie Sclar Xiang Lorraine Li Liwei Jian ... Sean Welleck Xiang Ren Allyson Ettinger Zaïd Harchaoui Yejin Choi ReLM LRM 201 388 0 29 May 2023
Break It Down: Evidence for Structural Compositionality in Neural Networks Michael A. Lepori Thomas Serre Ellie Pavlick 99 37 0 26 Jan 2023