# Learning Modular Exponentiation with Transformers

arXiv: https://arxiv.org/abs/2506.23679 · HTML: https://mlsanity.com/paper/2506.23679/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [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)
- [How to use and interpret activation patching](https://mlsanity.com/paper/2404.15255/) (2024)
- [A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models](https://mlsanity.com/paper/2407.02646/) (2024)
- [A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis](https://mlsanity.com/paper/2305.15054/) (2023)
- [Understanding Addition in Transformers](https://mlsanity.com/paper/2310.13121/) (2023)
- [Learning the greatest common divisor: explaining transformer predictions](https://mlsanity.com/paper/2308.15594/) (2023)
- [Systematic Generalization and Emergent Structures in Transformers Trained on Structured Tasks](https://mlsanity.com/paper/2210.00400/) (2022)
- [Grokking Modular Polynomials](https://mlsanity.com/paper/2406.03495/) (2024)
- [Murmurations of elliptic curves](https://mlsanity.com/paper/2204.10140/) (2022)

## Abstract (arXiv)

Modular exponentiation is crucial to number theory and cryptography, yet remains largely unexplored from a mechanistic interpretability standpoint. We train a 4-layer encoder-decoder Transformer model to perform this operation and investigate the emergence of numerical reasoning during training. Utilizing principled sampling strategies, PCA-based embedding analysis, and activation patching, we examine how number-theoretic properties are encoded within the model. We find that reciprocal operand training leads to strong performance gains, with sudden generalization across related moduli. These synchronized accuracy surges reflect grokking-like dynamics, suggesting the model internalizes shared arithmetic structure. We also find a subgraph consisting entirely of attention heads in the final layer sufficient to achieve full performance on the task of regular exponentiation. These results suggest that transformer models learn modular arithmetic through specialized computational circuits, paving the way for more interpretable and efficient neural approaches to modular exponentiation.