Savlar4 sources healthy · latest episode 15 Oct 2026
opinion claim

The speaker thinks interpretability uses “feature” too broadly and that more precise terminology is probably needed.

Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sept 2026

In their words

The transcript segments this claim was taken from

“In interpretability, we seem to call everything a feature.”
“So we probably need to get some better language here,”
“but they call them atoms or whatever.”
Play from 17:57Report a misattribution
75%how strongly it was put, not whether it is true
40%importance to the conversation
97%confidence the claim was read correctly