MATS Applications Open (Due Aug 29)

Neel Nanda · 19 Aug 2025

Neel Nanda did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
Complete reverse-engineering of neural networks is a less promising research direction than studying model biology and applying interpretability usefully

Their wordsI'm now fairly pessimistic about ambitious interpretability (i.e. complete reverse-engineering), and I'm excited about model biology (studying qualitative high-level properties of models) and applied interpretability (rigorously doing useful things with interp).
Our reading
Sparse autoencoders are a useful interpretability tool but are often used wastefully when a simpler, more obvious method would work as well or better

Their wordsI'm more agnostic about the best techniques, things like sparse autoencoders are a useful tool, but easy to waste effort using when a simpler method is sufficient or better - start by doing the obvious thing!
Our reading
Research taste, the harder-to-learn conceptual skills behind good research strategy, takes a long time to develop but very little time to apply once acquired

Their wordsMy model is that research requires a mix of skills. The day-to-day coding and execution is crucial. But there's also a set of harder-to-learn conceptual skills, collectively called research taste. These skills take a long time to gain because they have poor feedback loops, but they take very little time to use.

Keep reading

The other pieces are the ones whose claims are worded most like this one's. That measures language, not agreement: they may argue the opposite.