In-Context Learning & "Model Systems" Interpretability (Stanford lecture 3) - Ekdeep Singh Lubana скачать в хорошем качестве

In-Context Learning & "Model Systems" Interpretability (Stanford lecture 3) - Ekdeep Singh Lubana

What counts as an explanation of how an LLM works? In our last Stanford guest lecture, Ekdeep explains the different levels of analysis in interpretability, and outlines his neuro-inspired "model systems approach". Plus, how in-context learning and many-shot jailbreaking are explained by LLM representations changing in-context (as a case study for that approach). 00:33 - What counts as an explanation? 04:47 - Levels of analysis & standard interpretability approaches 18:19 - The "model systems" approach to interp (Case study on in-context learning) 23:36 - How LLM representations change in-context 44:10 - Modeling ICL with rational analysis 1:10:54 - Conclusion & questions Read more about our research: https://www.goodfire.ai/research Follow us on X: https://x.com/GoodfireAI