This demo is a lot more useful for comparing word embeddings: https://www.cs.cmu.edu/~dst/WordEmbeddingDemo/index.html

You can choose which dimensions to show, pick which embeddings to show, and play with vector maths between them in a visual way

It doesn't show the whole set of embeddings, though I am sure someone could fix that, as well as adapting it to use the gpt-oss model instead of the custom (?) mini set it uses.

It looks like it's not handling UTF-8 at all and displaying it as if it were Latin-1

  "\u00e0\u00a7\u012d\u00e0\u00a6\u013e"

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.

I lets you inspect what actually constitutes a given cluster, for example it seems like the outer clusters are variations of individual words and their direct translations, rather than synonyms (the ones I saw at least).

> What do people learn from visualizations like this?

Applying the embeddings model to some dataset of yours of interest, and then a similar visualization, is where it gets cool because you can visually look at clusters and draw conclusions about the closeness of items in your own dataset

Embedding visualizations have helped identify bias in word embeddings (Word2Vec), debug entity resolution systems, and optimize document retrieval by revealing semantic clusters that inform better indexing strategies.

They are incomparable. Token embeddings generated with something like word2vec worked well because the networks are shallow and therefore the learned semantic data can be contained solely and independently within the embeddings themselves. Token embeddings as a part of an LLM (e.g. gpt-oss-20b) are conditioned on said LLM and do not have fully independent learned data, although as shown here there still can be some relationships preserved.

Embeddings derived from autoregressive language models apply full attention mechanisms to get something different entirely.

Yes, it's just yoinking the weights out of the embeddings layer.

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.

I can see the labels when I hover with the pointer

Typically these algorithms cluster by similarity (either euclidian or cosine).

The density of the clusters tend to have trends. In this case, the "yolk" has a lot of bizarre unicode tokens.