Sarah Wiegreffe
banner
sarah-nlp.bsky.social
Sarah Wiegreffe
@sarah-nlp.bsky.social
Research in NLP (mostly LM interpretability & explainability).
Assistant prof at UMD CS + CLIP.
Previously @ai2.bsky.social @uwnlp.bsky.social
Views my own.
sarahwie.github.io
I am also recruiting PhD students @univofmaryland.bsky.social for fall 2026 with interests in (causal/mechanistic) LM interpretability and its practical applications (steering, efficient adaptation, model editing, textual explanations for users, etc.).
July 16, 2025 at 11:09 PM
Thank you! Look forward to being colleagues.
June 26, 2025 at 7:24 AM
Thank you!
June 26, 2025 at 7:24 AM
Thank you!
June 26, 2025 at 7:24 AM
Thanks :))
June 26, 2025 at 7:24 AM
Thanks so much for all your support ☺️🥰
June 16, 2025 at 10:11 PM
Thank you!
June 16, 2025 at 4:11 AM
Thank you 😄
June 16, 2025 at 4:11 AM
☺️ come visit!
June 16, 2025 at 4:11 AM
Congrats Kristina! 😍
May 30, 2025 at 6:11 PM
🤖: "Great review, but it could be improved by doing [exact thing I wrote in subsequent sentences]"
April 25, 2025 at 2:37 AM
Where is version control and shared editing for keynote files?! 🤦‍♀️
April 25, 2025 at 2:36 AM
We are quite excited about the leaderboard and release, and are open to feedback to help this remain a living benchmark.
April 25, 2025 at 2:24 AM
See Yanai's thread for more info:
bsky.app/profile/yana...
💡 New ICLR paper! 💡
"On Linear Representations and Pretraining Data Frequency in Language Models":

We provide an explanation for when & why linear representations form in large (or small) language models.

Led by @jackmerullo.bsky.social, w/ @nlpnoah.bsky.social & @sarah-nlp.bsky.social
April 25, 2025 at 2:21 AM
2) On the connection between linear relational embeddings in LMs and frequency of relations in pretraining data
- Led by @jackmerullo.bsky.social w/ @nlpnoah.bsky.social @yanai.bsky.social
- arxiv.org/abs/2504.12459
- Yanai is presenting the poster tomorrow 04/26 10am-12:30pm (Hall 3+Hall 2B #236)!
April 25, 2025 at 2:20 AM
Reposted by Sarah Wiegreffe
I'm in Singapore for ICLR to present this paper:
Tomorrow, April 26th, 10-12:30 in Hall 3+2B #236
Come check it out!

arxiv.org/abs/2504.12459
April 25, 2025 at 1:55 AM