LLM-Visualized – Interactive 3D and 2D Visualization of GPT-2
Three.js renders real GPT-2 attention patterns you can actually explore interactively.

Visualize a 4K-param GPT learning in real-time with clickable layer explanations.
ML students, neural network researchers, educators
Karpathy's nanoGPT · Hugging Face Transformers documentation visualizations
Three.js renders real GPT-2 attention patterns you can actually explore interactively.
Karpathy's minigpt ported to TS, readable code instead of brevity Olympics.
Type a name and you can literally watch characters turn into IDs, 16‑dim embeddings get added with positional encodings, and causal attention matrices animate per head — all matched numerically to Karpathy's 244‑line microGPT. The implementation is pure TypeScript (no ML libs) and includes a helpful scrollable sidebar with the reference math, which makes this an excellent, low‑friction learning tool — more pedagogical deep dive than research innovation.
Karpathy's microGPT in the browser with live loss curves, but pedagogical only—no production value.
Real-time world map of your connections makes invisible network activity visible.
Karpathy's microgpt in C99, proves tiny coordinated models beat single large models on logic.