Log inSign up
Image
user avatar
Aaron Mueller
@amuuueller
Asst. Prof. in CS at @BU_Tweets ≡ {Mechanistic, causal} {interpretability, NLP}
Boston
aaronmueller.github.io
Joined September 2015
736
Following
1,970
Followers
RepliesMedia
  • user avatar
    Aaron Mueller
    @amuuueller
    4h
    Have enjoyed using Silico! We gave it descriptions of relatively complex translation/interpretability experiments, and it found simpler ways to get evidence before working through it end-to-end. Saved me and a student a lot of time iterating. I then gave @divapp213 the reins...
    user avatar
    Goodfire
    @GoodfireAI
    Aug 4
    Silico, the platform for ambitious AI research, is publicly available today. AI is advancing fast. The tools to understand it need to advance even faster. Silico lets you interpret and train your models at frontier scale. Learn more + get access 🧵
    Image
    00:00
  • user avatar
    Aaron Mueller
    @amuuueller
    Jul 27
    Tired of writing NeurIPS rebuttals? Take a break by registering to attend the New England Mechanistic Interpretability workshop (deadline today)!
  • user avatar
    Aaron Mueller
    @amuuueller
    Jun 29
    If you'll be at ACL or ICML this year, come check out the work from our group and collaborators - summary 🧵 below. Lots to like for those into {mechanistic, developmental, pragmatic} interpretability! I'll be at ACL; say hi!
    Image
  • user avatar
    Aaron Mueller
    @amuuueller
    Jun 10
    The New England Mechanistic Interpretability (NEMI) workshop is coming to BU on Aug. 14! Join us for talks, a panel, food, and plenty of opportunities to connect with the many great researchers in the area. Register and help spread the word!
    user avatar
    Gabriel Franco
    @gvsfranco
    Jun 10
    🧠🤖 The 2026 New England Mechanistic Interpretability (NEMI) Workshop will be Aug. 14 at Boston University! Help spread the word and join the New England mech interp community! Registration and submission info in thread:👇
    Image
  • user avatar
    Aaron Mueller
    @amuuueller
    Mar 24
    Mechanisms help us understand why LLMs behave how they do, but our understanding often doesn’t generalize to new data. What’s missing here? How do we know when our evidence is reliable enough to predict future behaviors? Causality gives us answers. Led by @_shruti_joshi_!
    user avatar
    Shruti Joshi
    @_shruti_joshi_
    Mar 20
    Mechanistic interpretability aims to understand models — and the more superhuman or incoherent they become, the more we need that understanding to be reliable. We propose a framework for this, drawing on established tools from causal reasoning and statistical identifiability: 🧵
    Image
    00:00