[minimaxir]

Not everything has to be directly informative or solve a problem. Sometimes data visualization can look pretty for pretty's sake.

Dimensionality reduction/clustering like this may be less useful for identifying trends in token embeddings, but for other types of embeddings it's extremely useful.

[diwank]

Agreed. The fact that it has any structure at all is fascinating (and super pretty). Could signal at interesting internal structures. I would love to see a version for Qwen-3 and Mistral too!

I wonder if being trained on significant amounts of synthetic data gave it any unique characteristics.