RowanWang

Karma: 282

https://rowankwang.com/

Modifying LLM Beliefs with Synthetic Document Finetuning

RowanWang, Johannes Treutlein, Avery, Ethan Perez, Fabien Roger and Sam Marks

Apr 24, 2025, 9:15 PM

70 points

12 comments2 min readLW link

(alignment.anthropic.com)

Some Lessons Learned from Studying Indirect Object Identification in GPT-2 small

RowanWang, Alexandre Variengien, Arthur Conmy, Buck and jsteinhardt

Oct 28, 2022, 11:55 PM

101 points

9 comments9 min readLW link 2 reviews

(arxiv.org)

Gears-Level Mental Models of Transformer Interpretability

RowanWangMar 29, 2022, 8:09 PM

73 points

4 comments6 min readLW link

Lessons After a Couple Months of Trying to Do ML Research

RowanWangMar 22, 2022, 11:45 PM

70 points

8 comments6 min readLW link