Skip to content

@Confirm-Solutions Confirm Labs

Change the repository type filter

All

    Repositories list

    16 repositories

    • confirmlabs

      Public
      confirmlabs.org
      Jupyter Notebook
      •0•2•1•1•Updated Nov 20, 2025Nov 20, 2025

    • SAELens

      Public
      Jupyter Notebook
      •
      MIT License
      •0•0•0•0•Updated Oct 26, 2025Oct 26, 2025

    • sae_vis

      Public
      Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
      Python
      •
      MIT License
      •46•0•0•0•Updated Oct 26, 2025Oct 26, 2025

    • SAEBench

      Public
      Python
      •37•0•0•0•Updated Oct 26, 2025Oct 26, 2025

    • delphi

      Public
      Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models know themselves through…
      Python
      •
      Apache License 2.0
      •55•0•0•0•Updated Jun 13, 2025Jun 13, 2025

    • dailyreport

      Public
      Python
      •0•0•0•0•Updated Oct 8, 2024Oct 8, 2024

    • collab

      Public
      repository for sharing / working on code with collaborators
      Jupyter Notebook
      •0•0•0•0•Updated Sep 14, 2024Sep 14, 2024

    • imprint

      Public
      The Imprint Project
      Jupyter Notebook
      •
      BSD 3-Clause "New" or "Revised" License
      •3•13•12•0•Updated Sep 9, 2024Sep 9, 2024

    • share

      Public
      Jupyter Notebook
      •2•3•0•0•Updated Jul 31, 2024Jul 31, 2024

    • flrt

      Public
      Fluent student-teacher redteaming
      Jupyter Notebook
      •
      MIT License
      •4•23•3•0•Updated Jul 25, 2024Jul 25, 2024

    • dreamy

      Public
      Fluent dreaming for language models
      Python
      •
      MIT License
      •2•13•1•0•Updated Jul 22, 2024Jul 22, 2024

    • adv-grad-text2text

      Public
      0•0•0•0•Updated Mar 17, 2024Mar 17, 2024

    • align-transformers

      Public
      Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
      Python
      •
      Apache License 2.0
      •97•0•0•0•Updated Jul 3, 2023Jul 3, 2023

    • catalog

      Public
      Python
      •
      MIT License
      •0•1•0•0•Updated Jun 27, 2023Jun 27, 2023

    • confirmasaurus

      Public archive
      Jupyter Notebook
      •0•3•43•11•Updated Jun 24, 2023Jun 24, 2023

    • Imprint-Presentations

      Public
      Imprint presentation material.
      TeX
      •0•0•0•0•Updated Feb 22, 2023Feb 22, 2023