This is one of the talks given by a PIBBSS Fellow at the PIBBSS '23 Symposium.

Abstract: Computational Neuroscience has fruitfully posited that computations and representations in brains of behaving animals can be understood in terms of the geometric features of neural population activity. This has lead to a shift from circuit search to understanding population geometry directly to understand and theorize about neural system. Can this viewpoint be usefully imported into interpretability? I'll present some simple initial findings that show geometric regularities in toy LLMs. These regularities can be understood both as non-behavioral measures that might identify model capabilities or as empirical findings in search for a theory. I'll end with a brief sketch of a further research program this viewpoint suggests.

Watch more videos like this on our channel, and subscribe for similar content. Apply to work on such problems on our Website www.pibbss.ai