Nice post by Apart Research (who are giving me mentorship during my skilling-up in AI safety!). The bar plot is 😬.

New Anthropic research paper: Scaling Monosemanticity. The first ever detailed look inside a leading large language model. Read the blog post here: anthropic.com/research/mappi…

We're sharing progress toward understanding the neural activity of language models. We improved methods for training sparse autoencoders at scale, disentangling GPT-4’s internal representations into 16 million features—which often appear to correspond to understandable concepts.

steering ai is an imperfect art. that's what makes it fun. neuronpedia.org/gemma-scope#st…