Loading activity…
@sheridan_feucht
PhD student working on LLM interpretability with @davidbau and @byron_c_wallace. Undergrad @Brown_NLP '23. (they/them)
AI
A speaker says they'll discuss two “How LLMs Read” case studies at 9:10 a.m. on October 29.
AI
A researcher sharing a new preprint says they used the heads to create a simple logit lens for image tokens after finding they were responsible for OCR in vision-language models.
