3 repos
m9h/spinning-up-in-mech-interp
Spinning Up in Mechanistic Interpretability — a controls-first, open-weights curriculum from vision…
0
52 commits
callummcdougall/ARENA_2.0
Resources for skilling up in AI alignment research engineering. Covers basics of deep learning,…
248
531 commits
m9h/tri-lens
Do three interpretability instruments agree about the same activation? J-lens vs NLA vs SAE, with…
1
3 commits
