---
title: "Show HN: LLM-Visualized – Interactive 3D and 2D Visualization of GPT-2"
slug: "show-hn-llm-visualized-interactive-3d-and-2d-visualization-of-gpt-2"
date: 2026-03-19
category: community
tags: []
language: en
sources_count: 1
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/show-hn-llm-visualized-interactive-3d-and-2d-visualization-of-gpt-2
---

# Show HN: LLM-Visualized – Interactive 3D and 2D Visualization of GPT-2

**Published**: 2026-03-19 | **Category**: community | **Sources**: 1

---

## 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.

---

## Summary

- 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.
- 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.

---

## Why it matters

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

- 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.
- 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.

---


## FAQ

**Q:** What is Show HN about?

**A:** - 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.

**Q:** Why does it matter?

**A:** 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.

**Q:** What are the key takeaways?

**A:** 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.. 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.

---

## Related Topics

- —

---

## Sources

- [Show HN: LLM-Visualized – Interactive 3D and 2D Visualization of GPT-2](https://www.llm-visualized.com/) - Hacker News AI

---

## About This Article

This article is a synthesis of 1 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-03-20*