Show HN: LLM-Visualized – Interactive 3D and 2D Visualization of GPT-2
TL;DR
A developer built an interactive 3D and 2D visualization of GPT-2 Small (124M parameters) showing real activations and attention scores from an actual forward pass.
Key Points
- The 3D view uses Three.js; the 2D view is plain HTML/CSS/JS with no framework dependencies.
- The goal is to make transformer internals visually tangible without drowning in math.
- It is an open-source learning tool, not a commercial product.
Nauti's Take
Choosing GPT-2 as the teaching model is smart – old enough to be fully documented, relevant enough to still matter. The combination of real activations instead of synthetic examples with a 3D view is unusual and deserves attention.
Whether Three. js is the right foundation for serious interpretability tooling is debatable, but for a first visual impression it works well.
Anyone learning Mechanistic Interpretability will find this a solid starting point, better than most explainer videos out there.
Context
Understanding LLMs beyond textbook diagrams requires seeing real activations from a running model, which is a fundamentally different experience. GPT-2 is small enough to run in a browser yet complex enough to demonstrate all core transformer mechanisms. Tools like this significantly lower the barrier for developers and researchers who have previously only interacted with abstract API outputs.
Sources