Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on TopoNets: High performing vision and language models with brain-like topography. Parent comment
This is true. The features closer together now have much stronger semantic overlap. You can watch how the weights self-organize in a GPT here: https://toponets.github.io/webpage_assets/banner_video.mp4
We're already studying the effects of topographic structure on polysemanticity.
There are no comments on this comment yet.
This is true. The features closer together now have much stronger semantic overlap. You can watch how the weights self-organize in a GPT here: https://toponets.github.io/webpage_assets/banner_video.mp4
We're already studying the effects of topographic structure on polysemanticity.