This talk covers the fundamentals of mechanistic interpretability: what it is, why it might be impactful for alignment, and how you can get involved. It is most useful for people who are either new to AI safety, or limited knowledge about mechanistic interpretability. The speakers hope you gain insights into what interpretability research can look like, and whether it is a good fit for you. They also discuss some of the other work being done in technical alignment research.
EAG Talks