Principles for Picking Practical Interpretability Projects
Published on July 15, 2025 5:38 PM GMTThanks to Neel Nanda and Helena Casademunt for feedback on a draft.In a previous post, I argued that some interpretability researchers should prioritize showcasing downstream applications of interpretability work; I call …
Thanks to Neel Nanda and Helena Casademunt for feedback on a draft. In a previous post, I argued that some interpretability researchers should prioritize showcasing downstream applications of interp… [+27743 chars]