Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
withmartian 's Collections
Fine Tuned LLMs for CARROT
k-steering
Transferring Activation Features for model interventions
TinySQL
Blog: Activations transfer for model interventions.

k-steering

updated 29 days ago

Collecting datasets used for our paper on multi-attribute steering using gradient descent.

Upvote
1

  • withmartian/binary_truthful

    Viewer • Updated Apr 25 • 5.88k • 9

  • withmartian/binary_toxic

    Viewer • Updated Apr 25 • 251k • 13

  • withmartian/binary_bbq

    Viewer • Updated Apr 28 • 175k • 25

  • withmartian/debate_style_agnostic_questions

    Viewer • Updated Sep 5 • 978 • 28

  • withmartian/tone_agnostic_questions

    Viewer • Updated Sep 5 • 1.18k • 19

  • withmartian/DEBATEMIX

    Viewer • Updated 29 days ago • 200 • 44

  • withmartian/TONEBANK

    Viewer • Updated 29 days ago • 200 • 25
Upvote
1
  • Collection guide
  • Browse collections
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs