RGRGRG

Karma: 138

Cross-Layer Transcoders are incentivized to learn Unfaithful Circuits

Georg Lange, RGRGRG, Kat Dearstyne and Kamal Maher

2 Feb 2026 21:32 UTC

40 points

6 comments18 min readLW link

Alternative Models of Superposition

zroe1 and RGRGRG

11 Aug 2025 15:52 UTC

20 points

6 comments5 min readLW link

Seeking Feedback on My Mechanistic Interpretability Research Agenda

RGRGRG12 Sep 2023 18:45 UTC

5 points

1 comment3 min readLW link

Thoughts about the Mechanistic Interpretability Challenge #2 (EIS VII #2)

RGRGRG28 Jul 2023 20:44 UTC

26 points

5 comments20 min readLW link

[Question] Best Ways to Try to Get Funding for Alignment Research?

RGRGRG4 Apr 2023 6:35 UTC

10 points

6 comments1 min readLW link