Zach Studdiford
@zstuddiford.bsky.social
Undergrad researcher
@UWMadison.bsky.social | Language and cognition | Representational alignment in LLMs
@UWMadison.bsky.social | Language and cognition | Representational alignment in LLMs
We’re drowning in language models — there are over 2 mil. of them on Huggingface! Can we use some of them to understand which computational ingredients — architecture, scale, post-training, etc. – help us build models that align with human representations? Read on to find out 🧵
October 21, 2025 at 4:55 PM
We’re drowning in language models — there are over 2 mil. of them on Huggingface! Can we use some of them to understand which computational ingredients — architecture, scale, post-training, etc. – help us build models that align with human representations? Read on to find out 🧵