poloclub /transformer-explainer

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

★ 9,165⑂ 1,080👁 76⑃ 56● 32▤ 1
JavaScriptMITCreated 2024-05-16poloclub.github.io/transformer-explainer/
下载:v0.0.1transformer-explainer-0.0.1 ↓0.0.12024-06-11
+3
日增长
9,165
stars
1,080
forks
76
watchers
56
prs
32
issues
1
releases

README

Transformer Explainer: Interactive Learning of Text-Generative Models

Transformer Explainer is an interactive visualization tool designed to help anyone learn how Transformer-based models like GPT work. It runs a live GPT-2 model right in your browser, allowing you to experiment with your own text and observe in real time how internal components and operations of the Transformer work together to predict the next tokens. Try Transformer Explainer at http://poloclub.github.io/transformer-explainer and watch a demo video on YouTube https://youtu.be/TFUc41G2ikY.





 Live Demo

Try Transformer Explainer: http://poloclub.github.io/transformer-explainer

 Research Paper

Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentations.
Aeree Cho, Grace C. Kim, Alexander Karpekov, Seongmin Lee, Alec Helbling, Benjamin Hoover, Zijie J. Wang, Minsuk Kahng, Duen Horng Chau.
_Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems._

 How to run locally

 Prerequisites

- Node.js v20 or higher
- NPM v10 or higher

 Steps

bash
git clone https://github.com/poloclub/transformer-explainer.git
cd transformer-explainer
npm install
npm run dev


Then, on your web browser, access http://localhost:5173.

 Credits

Transformer Explainer was created by Aeree Cho, Grace C. Kim, Alexander Karpekov, Alec Helbling, Jay Wang, Seongmin Lee, Benjamin Hoover, and Polo Chau at the Georgia Institute of Technology.

 Citation

bibTeX
@inproceedings{cho2026transformer,
  title={Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation},
  author={Cho, Aeree and Kim, Grace C and Karpekov, Alexander and Lee, Seongmin and Helbling, Alec and Hoover, Benjamin and Wang, Zijie J and Kahng, Minsuk and Chau, Duen Horng},
  booktitle={Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},
  pages={1--21},
  year={2026}
}


 License

The software is available under the MIT License.

 Contact

If you have any questions, feel free to open an issue or contact Aeree Cho or any of the contributors listed above.

 More AI explainers to check out

- Diffusion Explainer for learning how Stable Diffusion transforms text prompt into image
- CNN Explainer
- GAN Lab for playing with Generative Adversarial Networks in browser

Top issues

Latest release

v0.0.1 v0.0.1 2024-06-11

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON