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

arXiv: https://arxiv.org/abs/2609.17571 · HTML: https://mlsanity.com/paper/2609.17571/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets](https://mlsanity.com/paper/2201.02177/) (2022)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Explaining grokking through circuit efficiency](https://mlsanity.com/paper/2309.02390/) (2023)
- [AtP*: An efficient and scalable method for localizing LLM behaviour to components](https://mlsanity.com/paper/2403.00745/) (2024)
- [Can Neural Network Memorization Be Localized?](https://mlsanity.com/paper/2307.09542/) (2023)
- [How much do language models memorize?](https://mlsanity.com/paper/2505.24832/) (2025)
- [Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition](https://mlsanity.com/paper/2407.12332/) (2024)
- [Localizing Paragraph Memorization in Language Models](https://mlsanity.com/paper/2403.19851/) (2024)
- [Differential learning kinetics govern the transition from memorization to generalization during in-context learning](https://mlsanity.com/paper/2412.00104/) (2024)
- [Analyzing Memorization in Large Language Models through the Lens of Model Attribution](https://mlsanity.com/paper/2501.05078/) (2025)
- [Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer](https://mlsanity.com/paper/2506.01115/) (2025)
- [Mechanistic Insights into Grokking from the Embedding Layer](https://mlsanity.com/paper/2505.15624/) (2025)
- [Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds](https://mlsanity.com/paper/2605.09724/) (2026)
- [ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior](https://mlsanity.com/paper/2505.20076/) (2025)
- [Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers](https://mlsanity.com/paper/2601.09049/) (2026)
- [Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets](https://mlsanity.com/paper/2605.15787/) (2026)

## Abstract (arXiv)

Where in a Transformer is the change from memorization to generalization functionally expressed? We introduce Transition Games--behavior-aligned exact activation games with paired non-generalizing controls--and find distributed utility gain with a prospective block-0 attention bias; selected degree-two modes account for 67--92% of its addition contrast across replacement games, and a disjoint exact path study confirms that block-1 MLP mediates more of their effect than all other tested downstream paths in 12/12 pairs. The sharper "MLP memorizes, attention generalizes" prediction instead reverses (-.331 bits/example at the memory anchor; 0/12 in the predicted direction), while routing onset, global rank collapse, and a prime-invariant architecture ridge also fail, identifying grokking here as spectral recoding of an existing distributed circuit rather than a module switch.