Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our tool helps users understand complex Transformer concepts by integrating a model overview and enabling smooth transitions across abstraction levels of mathematical operations and model structures. It runs a live GPT-2 instance locally in the user's browser, empowering users to experiment with their own input and observe in real-time how the internal components and parameters of the Transformer work together to predict the next tokens. Our tool requires no installation or special hardware, broadening the public's education access to modern generative AI techniques. Our open-sourced tool is available at https://poloclub.github.io/transformer-explainer/. A video demo is available at https://youtu.be/ECR4oAwocjs.
@article{arxiv.2408.04619,
title = {Transformer Explainer: Interactive Learning of Text-Generative Models},
author = {Aeree Cho and Grace C. Kim and Alexander Karpekov and Alec Helbling and Zijie J. Wang and Seongmin Lee and Benjamin Hoover and Duen Horng Chau},
journal= {arXiv preprint arXiv:2408.04619},
year = {2024}
}