# Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs

arXiv: https://arxiv.org/abs/2402.09469 · HTML: https://mlsanity.com/paper/2402.09469/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- First posted on arXiv 12 Feb 2024.

## Placed in

- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

## Built on by (most cited first, 22 of 22)

- [Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models](https://mlsanity.com/paper/2406.14852/) (2024)
- [Why Larger Language Models Do In-context Learning Differently?](https://mlsanity.com/paper/2405.19592/) (2024)
- [Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability](https://mlsanity.com/paper/2407.15720/) (2024)
- [Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers](https://mlsanity.com/paper/2405.05219/) (2024)
- [Circuit Complexity Bounds for RoPE-based Transformer Architecture](https://mlsanity.com/paper/2411.07602/) (2024)
- [Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time](https://mlsanity.com/paper/2408.13233/) (2024)
- [The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity](https://mlsanity.com/paper/2412.06148/) (2024)
- [Looped ReLU MLPs May Be All You Need as Practical Programmable Computers](https://mlsanity.com/paper/2410.09375/) (2024)
- [HSR-Enhanced Sparse Attention Acceleration](https://mlsanity.com/paper/2410.10165/) (2024)
- [Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond](https://mlsanity.com/paper/2405.03251/) (2024)
- [Theoretical Constraints on the Expressive Power of mathsfRoPE-based Tensor Attention Transformers](https://mlsanity.com/paper/2412.18040/) (2024)
- [Towards Infinite-Long Prefix in Transformer](https://mlsanity.com/paper/2406.14036/) (2024)
- [On Computational Limits of FlowAR Models: Expressivity and Efficiency](https://mlsanity.com/paper/2502.16490/) (2025)
- [Sequential Group Composition: A Window into the Mechanics of Deep Learning](https://mlsanity.com/paper/2602.03655/) (2026)
- [Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers](https://mlsanity.com/paper/2501.10688/) (2025)
- [Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches](https://mlsanity.com/paper/2503.01314/) (2025)
- [When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?](https://mlsanity.com/paper/2502.16912/) (2025)
- [On the geometry and topology of representations: the manifolds of modular addition](https://mlsanity.com/paper/2512.25060/) (2025)
- [Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding](https://mlsanity.com/paper/2503.11108/) (2025)
- [Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency](https://mlsanity.com/paper/2503.14076/) (2025)
- [Latent Algorithmic Structure Precedes Grokking: A Mechanistic Study of ReLU MLPs on Modular Arithmetic](https://mlsanity.com/paper/2603.23784/) (2026)
- [A Polyphonic Conception of AI Understanding](https://mlsanity.com/paper/2609.36079/) (2026)

## Abstract (arXiv)

In the evolving landscape of machine learning, a pivotal challenge lies in deciphering the internal representations harnessed by neural networks and Transformers. Building on recent progress toward comprehending how networks execute distinct target functions, our study embarks on an exploration of the underlying reasons behind networks adopting specific computational strategies. We direct our focus to the complex algebraic learning task of modular addition involving k inputs. Our research presents a thorough analytical characterization of the features learned by stylized one-hidden layer neural networks and one-layer Transformers in addressing this task. A cornerstone of our theoretical framework is the elucidation of how the principle of margin maximization shapes the features adopted by one-hidden layer neural networks. Let p denote the modulus, Dp denote the dataset of modular arithmetic with k inputs and m denote the network width. We demonstrate that a neuron count of  m ≥ 22k-2 · (p-1) , these networks attain a maximum  L2,k+1 -margin on the dataset  Dp . Furthermore, we establish that each hidden-layer neuron aligns with a specific Fourier spectrum, integral to solving modular addition problems. By correlating our findings with the empirical observations of similar studies, we contribute to a deeper comprehension of the intrinsic computational mechanisms of neural networks. Furthermore, we observe similar computational mechanisms in attention matrices of one-layer Transformers. Our work stands as a significant stride in unraveling their operation complexities, particularly in the realm of complex algebraic tasks.