Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

Why we made this list:

The interpretability team at Apollo Research wrapped up a few projects recently[1]. In order to decide what we’d work on next, we generated a lot of different potential projects. Unfortunately, we are computationally bounded agents, so we can't work on every project idea that we were excited about!
Previous lists of project ideas (such as Neel's collation of 200 Concrete Open Problems in Mechanistic Interpretability) have been very useful for people breaking into the field. But for all its merits, that list is now over a year and a half old. Therefore, many project ideas in that list aren’t an up-to-date reflection of what some researchers consider the frontiers of mech interp.

We therefore thought it would be helpful to share our list of project ideas!

Comments and caveats:

---

Outline:

(01:54) Foundational work on sparse dictionary learning for interpretability

(19:22) Applied interpretability

(26:36) Intrinsic interpretability

(29:11) Understanding features (not SDL)

(30:22) Theoretical foundations for interpretability

(35:01) Meta-research and philosophy

(36:18) Engineering

The original text contained 1 footnote which was omitted from this narration.

---

First published:
July 18th, 2024

Source:
https://www.lesswrong.com/posts/KfkpgXdgRheSRWDy8/a-list-of-45-mech-interp-project-ideas-from-apollo-research

---

“A List of 45+ Mech Interp Project Ideas from Apollo Research’s Interpretability Team” by Lee Sharkey, Lucius Bushnaq, Dan Braun, StefanHex, Nicholas Goldowsky-Dill

LessWrong (30+ Karma)