attention-galaxy runs SmolLM2-135M in-browser with live next-token and attention visualization
GitHub talhatahir-10xe/attention-galaxy published this on Oct 11, 2026 (source: github.com).
Developer talhatahir-10xe released attention-galaxy, an open tool that runs SmolLM2-135M fully in the browser via onnxruntime-web (int8, no server) and, for each generated token, shows next-token candidates with probabilities plus labeled attention links back to earlier tokens. A live demo is on GitHub Pages; the author notes strong first-token attention sink behavior that initially looked like a bug.