Embedding Space Viewer

The site of analysis for this project is the geography of the semantic embedding space itself. You are looking at a compressed model of this space, populated with 700 datapoints written in the English language, self-authored.

Processing language and meaning in this way creates a high-dimensional, difficult-to-wrangle topography. So, for the purpose of human understanding, I have distilled the infinite-seeming geography of 1536 dimensions into a three-dimensional realm for you to navigate freely. You will see three clusters of meaning orbiting this space, having arranged themselves according to the following local gravities: a) the human experience; b) earth's ecologies and biomes, and c) earth's modern nations.

The purpose of this project is to better represent the tendencies and potential biases of the [ ] model, a tool that is [ ] to the fallable data on which it has been trained.

How to interact:

Long-click and drag to pan embedding space visualisation.
Click once anywhere to pause/resume animation.
Hover over any sprite to see the data point it represents.
Corresponding data points in the other semantic clusters, as interpreted by the text-embedding model, will also be revealed.

This project has not been designed for mobile use. Please view on desktop for full functionality.