[mucle6]

I wish they had comments about what the clusters are and what the "empty loops" are

[mortenjorck]

I suppose an unavoidable effect of the dimensionality reduction process is that clusters of correlations across dozens of dimensions are by nature hard to describe.

This actually seems like a potentially great application for LLMs – generating a semantic description of an n-dimensional correlation.

[mucle6]

This does sound like a fun use case, but I wouldn't even mind being allowed to browse 2d representations to get an intuition of the clusterings

[ernaem]

By the way, if you're browsing from the desktop, there's a 3D/2D toggle in the top left corner of the Overview page.