Skip to content
View pavanyellow's full-sized avatar
3 followers · 2 following

Achievements

Achievement: Pair Extraordinairex2Achievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3
BetaSend feedback

Achievements

Achievement: Pair Extraordinairex2Achievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3
BetaSend feedback
Block or Report

Block or report pavanyellow

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned

  1. feature-steering feature-steering Public

    Controlling LLM outputs by activating/suppressing feature vectors

    Jupyter Notebook

  2. TransformerLensOrg/TransformerLens TransformerLensOrg/TransformerLens Public

    A library for mechanistic interpretability of GPT-style language models

    Python 1.1k 233

  3. sparse-autoencoder sparse-autoencoder Public

    Interpreting the ultra-low density cluster in sparse autoencoders from Anthropic's Towards Monosemanticity work

    Jupyter Notebook

  4. alpha-zero-general alpha-zero-general Public

    Forked from suragnair/alpha-zero-general

    Sparse Autoencoders for extracting new superhuman concepts from AlphaZero and Pluribus

    Python