News for hackers. Stuff that matters.
Re:Show HN: We've open-sourced our LLM attention visualizati... by dimatura on Sunday June 09, 2024 @09:08PM (#40629090)
That OpenAI work is more elaborate. It trains an additional network in such a way that it encodes what GPT is doing in terms of activations, but in a more interpretable way (hopefully). Here, as far as I can tell, it's visualizing the activation of the attention layers directly.

There are no comments on this comment yet.