Visualizing a modular-addition transformer: 2k vs 20k training steps reveal ring structure

Sauers_ · x · 2026-09-24

A striking visualization compares a modular-addition transformer at 2k vs 20k training steps: 113 possible output tokens arranged clockwise, each ring a number being added, color showing logprobs. By 20k steps the model develops clear ring structure — a vivid window into how transformers learn modular arithmetic (the Grokking phenomenon).

Related event: Visualization Shows How a Modular Addition Transformer Learns(2 posts)→

Original post →

More from Research

Research channel →