1. X
  2. Arnab Sen Sharma
Log inSign up
Arnab Sen Sharma
70 posts
user avatar
Arnab Sen Sharma
@arnab_api
Ph.D. student @KhouryCollege, working to make LLMs interpretable
Boston, MA
arnab-api.github.io
Joined September 2022
178
Following
306
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    Arnab Sen Sharma
    @arnab_api
    Nov 4, 2025
    How can a language model find the veggies in a menu? New pre-print where we investigate the internal mechanisms of LLMs when filtering on a list of options. Spoiler: turns out LLMs use strategies surprisingly similar to functional programming (think "filter" from python)! 馃У
    Image
  • user avatar
    Arnab Sen Sharma
    @arnab_api
    Apr 22
    Super excited to be attending @iclr_conf in Rio. Stop by our poster tomorrow morning (10:30am - 1:00pm) in Pavilion 4 (P4-#4001) to know about list-processing mechanisms in LMs. DMs are open. Please reach out if you want to meet up!
    user avatar
    Arnab Sen Sharma
    @arnab_api
    Nov 4, 2025
    How can a language model find the veggies in a menu? New pre-print where we investigate the internal mechanisms of LLMs when filtering on a list of options. Spoiler: turns out LLMs use strategies surprisingly similar to functional programming (think "filter" from python)! 馃У
    Image
  • user avatar
    Arnab Sen Sharma
    @arnab_api
    Oct 6, 2024
    Attending @COLM_conf in Philadelphia! Drop by our poster on Wednesday morning (Session 5, 11 am - 1 pm, #8) Would love to catch up and chat about interpretability. Give me a DM!
    user avatar
    Arnab Sen Sharma
    @arnab_api
    Apr 12, 2024
    How does Mamba store knowledge? Is it very different from transformers? New pre-print with @diatkinson and @davidbau, where we investigate the mechanisms of factual recall within Mamba.
    Image
  • user avatar
    Arnab Sen Sharma
    @arnab_api
    May 8, 2024
    Just reached Vienna to attend ICLR! Stop by our poster session tomorrow (10:45 am, Hall B, #131). Would love to chat with people about interpretability and AI alignment. DMs are open!
    user avatar
    David Bau
    @davidbau
    May 2, 2024
    Replying to @davidbau
    Does a holistic view of a subnetwork reveal higher-level structure beyond neurons, attention, vectors? In lre.baulab.info @arnab_api @evanqed @mengk20 @talhacklay @boknilev test the power of the Jacobian鈥攖he matrix derivative鈥攖o explain relations. Thu 10:45, Hall B 131
    Image
  • user avatar
    Arnab Sen Sharma
    @arnab_api
    Apr 12, 2024
    How does Mamba store knowledge? Is it very different from transformers? New pre-print with @diatkinson and @davidbau, where we investigate the mechanisms of factual recall within Mamba.
    Image

Log in or sign up for X

See what鈥檚 happening and join the conversation

Continue with phone
or
Log in with username or email
Terms路Privacy路Cookies路Accessibility路Ads Info路漏 2026 X Corp.
Advertisement
Advertisement