[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-70547":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":16,"starSnapshotCount":16,"syncStatus":34,"lastSyncTime":35,"discoverSource":36},70547,"transformer-explainer","poloclub\u002Ftransformer-explainer","poloclub","Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization",null,"https:\u002F\u002Fgithub.com\u002Fpoloclub\u002Ftransformer-explainer","JavaScript",7797,848,66,8,0,35,138,446,105,39.79,false,"main",[25,26,27,28,29,30],"generative-ai","gpt","deep-learning","langauge-model","llm","visualization","2026-06-12 02:02:34","# Transformer Explainer: Interactive Learning of Text-Generative Models\n\nTransformer 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:\u002F\u002Fpoloclub.github.io\u002Ftransformer-explainer and watch a demo video on YouTube https:\u002F\u002Fyoutu.be\u002FTFUc41G2ikY.\u003Cbr\u002F>\u003Cbr\u002F>\n[![MIT license](http:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-brightgreen.svg)](http:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n[![arxiv badge](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-2408.04619-red)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.04619)\n\n\u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FTFUc41G2ikY\" target=\"_blank\">\u003Cimg width=\"100%\" src='https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F0a4d8888-6555-4df5-bc71-77f1299115c3'>\u003C\u002Fa>\n\n## Live Demo\nTry Transformer Explainer: http:\u002F\u002Fpoloclub.github.io\u002Ftransformer-explainer\n\n## Research Paper\n\n[**Transformer Explainer: Interactive Learning of Text-Generative Models**](https:\u002F\u002Farxiv.org\u002Fabs\u002F2408.04619).\nAeree Cho, Grace C. Kim, Alexander Karpekov, Alec Helbling, Zijie J. Wang, Seongmin Lee, Benjamin Hoover, Duen Horng Chau.\n_Poster, IEEE VIS 2024._\n\n## How to run locally\n\n#### Prerequisites\n\n- Node.js v20 or higher\n- NPM v10 or higher\n\n#### Steps\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fpoloclub\u002Ftransformer-explainer.git\ncd transformer-explainer\nnpm install\nnpm run dev\n```\n\nThen, on your web browser, access http:\u002F\u002Flocalhost:5173.\n\n## Credits\n\nTransformer Explainer was created by \u003Ca href=\"https:\u002F\u002Faereeeee.github.io\u002F\" target=\"_blank\">Aeree Cho\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fchaeyeonggracekim\u002F\" target=\"_blank\">Grace C. Kim\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Falexkarpekov.com\u002F\" target=\"_blank\">Alexander Karpekov\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Falechelbling.com\u002F\" target=\"_blank\">Alec Helbling\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fzijie.wang\u002F\" target=\"_blank\">Jay Wang\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fseongmin.xyz\u002F\" target=\"_blank\">Seongmin Lee\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fbhoov.com\u002F\" target=\"_blank\">Benjamin Hoover\u003C\u002Fa>, and \u003Ca href=\"https:\u002F\u002Fpoloclub.github.io\u002Fpolochau\u002F\" target=\"_blank\">Polo Chau\u003C\u002Fa> at the Georgia Institute of Technology.\n\n## Citation\n\n```bibTeX\n@article{cho2024transformer,\n  title = {Transformer Explainer: Interactive Learning of Text-Generative Models},\n  shorttitle = {Transformer Explainer},\n  author = {Cho, Aeree and Kim, Grace C. and Karpekov, Alexander and Helbling, Alec and Wang, Zijie J. and Lee, Seongmin and Hoover, Benjamin and Chau, Duen Horng},\n  journal={IEEE VIS Poster},\n  year={2024}\n}\n```\n\n## License\n\nThe software is available under the [MIT License](https:\u002F\u002Fgithub.com\u002Fpoloclub\u002Ftransformer-explainer\u002Fblob\u002Fmain\u002FLICENSE).\n\n## Contact\n\nIf you have any questions, feel free to [open an issue](https:\u002F\u002Fgithub.com\u002Fpoloclub\u002Ftransformer-explainer\u002Fissues\u002Fnew\u002Fchoose) or contact [Aeree Cho](https:\u002F\u002Faereeeee.github.io\u002F) or any of the contributors listed above.\n\n## More AI explainers to check out\n\n- [**Diffusion Explainer**](https:\u002F\u002Fpoloclub.github.io\u002Fdiffusion-explainer) for learning how Stable Diffusion transforms text prompt into image\n- [**CNN Explainer**](https:\u002F\u002Fpoloclub.github.io\u002Fcnn-explainer)\n- [**GAN Lab**](https:\u002F\u002Fpoloclub.github.io\u002Fganlab) for playing with Generative Adversarial Networks in browser\n","Transformer Explainer 是一个交互式可视化工具，旨在帮助用户理解基于Transformer架构的模型（如GPT）的工作原理。该项目通过在浏览器中运行实时GPT-2模型，让用户能够输入自己的文本并即时观察模型内部组件如何协作以预测下一个词。其核心功能包括直观展示Transformer各层的操作细节，有助于学习者深入理解复杂的神经网络结构。此项目特别适合对自然语言处理和机器学习感兴趣的教育场景以及希望深入了解Transformer模型工作机制的研究人员和技术爱好者使用。",2,"2026-06-11 03:32:45","trending"]