# Low Rank and Sparse Fourier Structure in Recurrent Networks Trained on Modular Addition

arXiv: https://arxiv.org/abs/2503.22059 · HTML: https://mlsanity.com/paper/2503.22059/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 16 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets](https://mlsanity.com/paper/2201.02177/) (2022)
- [The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks](https://mlsanity.com/paper/2306.17844/) (2023)
- [Explaining grokking through circuit efficiency](https://mlsanity.com/paper/2309.02390/) (2023)
- [Grokking modular arithmetic](https://mlsanity.com/paper/2301.02679/) (2023)
- [Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition](https://mlsanity.com/paper/2407.12332/) (2024)
- [Feature emergence via margin maximization: case studies in algebraic tasks](https://mlsanity.com/paper/2311.07568/) (2023)
- [Emergence in non-neural models: grokking modular arithmetic via average gradient outer product](https://mlsanity.com/paper/2407.20199/) (2024)
- [Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks](https://mlsanity.com/paper/2312.08550/) (2023)
- [Grokking Modular Polynomials](https://mlsanity.com/paper/2406.03495/) (2024)

## Abstract (arXiv)

Modular addition tasks serve as a useful test bed for observing empirical phenomena in deep learning, including the phenomenon of grokking. Prior work has shown that one-layer transformer architectures learn Fourier Multiplication circuits to solve modular addition tasks. In this paper, we show that Recurrent Neural Networks (RNNs) trained on modular addition tasks also use a Fourier Multiplication strategy. We identify low rank structures in the model weights, and attribute model components to specific Fourier frequencies, resulting in a sparse representation in the Fourier space. We also show empirically that the RNN is robust to removing individual frequencies, while the performance degrades drastically as more frequencies are ablated from the model.