[trhway]

> how llms map to the brain

For the lower level - word embedings (word2vec, "King – Man + Woman = Queen") - one can see a similarity

https://www.nature.com/articles/d41586-019-00069-1 and https://gallantlab.org/viewer-huth-2016/

"The map reveals how language is spread throughout the cortex and across both hemispheres, showing groups of words clustered together by meaning."

[nyrikki]

That is the latent space.

Very different from a feed forward network with perceptrons, auttograd, etc...

Inner product spaces are fixed points, mapping between models is less surprising because the general case is a merger set IIRC.