[metalwhale]

This is interesting.

How can you retrieve the latent representation of the candidate LLMs? Some models do not have open weights (such as GPT-4), which means AFAIK it is impossible to directly access the hidden latent space through their API.

Am I missing something?

[danlenton]

We just initialize a random latent vector for each model, and then jointly train each of these unique latent vectors :)