News for hackers. Stuff that matters.
Re:Show HN: Llama 3.2 Interpretability with Sparse Autoencoders by omgwtfbyobbq on Friday November 22, 2024 @01:43AM (#42211658)
I think Robert Sapolsky's lectures on yt cover this to some degree around 115.

https://youtu.be/wLE71i4JJiM?feature=shared

Sometimes our cortex is in charge, sometimes other parts of our brain are, and we can't tell the difference. Regardless, if we try to justify it later, that justification isn't always coherent because we're not always using the part of our brain we consider to be rational.

Re:Show HN: Llama 3.2 Interpretability with Sparse Autoencoders by snthpy on Friday November 22, 2024 @08:48AM (#42213800)
Yes that was probably it because I rewatched that recently. Thanks!