Visual Word Embeddings is a fun visualization project that uses tensorflow embeddings to create and interactive, space-like 3D visualization. The project uses UMAP to reduce the dimensionality of the word embeddings, and then uses three.js to create an awesome looking plot. The project is designed to be interactive, allowing the user to rotate and zoom in on the plot as well as adding words to the plot to see how LLMs ’understand’ the semantics of words. This servers as a fun introduction to LLMs and word embeddings for students, something that I was looking for when learning about them.

First, download and install the dependencies:

npm i

Then, run the development server:

npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev

Open http://localhost:3000 with your browser to see the result.

You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.

This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.

To learn more about Next.js, take a look at the following resources:

• Next.js Documentation - learn about Next.js features and API.
• Learn Next.js - an interactive Next.js tutorial.

You can check out the Next.js GitHub repository - your feedback and contributions are welcome!

The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.

Check out our Next.js deployment documentation for more details.