Contributed Talk 5: Interpreting Grokked Transformers in Complex Modular Arithmetic

Grokking has been actively explored to reveal the mystery of delayed generalization. Identifying interpretable algorithms inside the grokked models is a suggestive hint to understanding its mechanism. In this work, beyond the simplest and well-studied modular addition, we observe the internal circuits learned through grokking in complex modular arithmetic via interpretable reverse engineering, which highlights the significant difference in their dynamics: subtraction poses a strong asymmetry on Transformer; multiplication requires cosine-biased components at all the frequencies in a Fourier domain; polynomials often result in the superposition of the patterns from elementary arithmetic, but clear patterns do not emerge in challenging cases; grokking can easily occur even in higher-degree formulas with basic symmetric and alternating expressions. We also introduce the novel progress measure for modular arithmetic; Fourier Frequency Sparsity and Fourier Coefficient Ratio, which not only indicate the late generalization but also characterize distinctive internal representations of grokked models per modular operation. Our empirical analysis emphasizes the importance of holistic evaluation among various combinations.