On: Visualizing GPT-OSS-20B embeddings

[kingstnap]

It's an interesting looking plot I suppose.

My guess is its the 2 largest principle components of the embedding.

But none of the points are labelled? There isn't a writeup on the page or anything?

[jablongo → kingstnap]

Usually PCA doesn't look quite like this so this is likely done using TSNE or UMAP, which are non parametric embeddings (they optimize a loss by modifying the embedded points directly). I can see labels if I mouseover the dots.

[terhechte → kingstnap]

I can see the labels when I hover with the pointer