News for hackers. Stuff that matters.
Re:Scaling Monosemanticity: Extracting Interpretable Feature... by canjobear on Wednesday May 22, 2024 @10:00AM (#40441108)
Neural network representation spaces seem to converge, regardless of architecture: https://arxiv.org/abs/2405.07987

It would make sense for the human mental latent spaces to also converge. The reason is that the latent space exists to model the environment, which is largely shared among humans.

There are no comments on this comment yet.