Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch

arXiv:2609.17571 · cs.LG, cs.AI · Submitted 2026-07-29 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-07-29

Updated: 2026-07-29

Comments: 27 pages, 10 figures. Code and data: https://github.com/cheshireyang/where-grokking-happens/releases/tag/v0.3.2

Code: https://github.com/cheshireyang/where-grokking-happens

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 1× in this paper · explained in 13 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks