Skip to content
@goodfire-ai

Goodfire

Understanding and intentionally designing the next frontier of safe and powerful AI systems.

Popular repositories Loading

  1. r1-interpretability r1-interpretability Public

    Open source interpretability artefacts for R1.

    Jupyter Notebook 169 10

  2. scribe scribe Public

    Python 66 14

  3. spd spd Public

    Stochastic Parameter Decomposition

    Python 61 32

  4. sdxl-turbo-interpretability sdxl-turbo-interpretability Public

    Jupyter Notebook 47 6

  5. goodfire-sdk goodfire-sdk Public archive

    Ember is a hosted API/SDK that lets you shape AI model behavior by directly controlling a model's internal units of computation, or "features". With Ember, you can modify features to precisely cont…

    Python 41 8

  6. causalab causalab Public

    Python 30 18

Repositories

Showing 10 of 10 repositories
  • spd Public

    Stochastic Parameter Decomposition

    goodfire-ai/spd’s past year of commit activity
    Python 61 MIT 32 30 (5 issues need help) 16 Updated Jan 30, 2026
  • simple_stories_train Public Forked from simple-stories/simple_stories_train

    Trains small LMs. Designed for training on SimpleStories

    goodfire-ai/simple_stories_train’s past year of commit activity
    Python 0 MIT 5 0 1 Updated Jan 27, 2026
  • causalab Public
    goodfire-ai/causalab’s past year of commit activity
    Python 30 18 5 2 Updated Jan 22, 2026
  • scribe Public
    goodfire-ai/scribe’s past year of commit activity
    Python 66 14 0 1 Updated Jan 8, 2026
  • goodfire-ai/memorization_kfac’s past year of commit activity
    Python 24 5 1 0 Updated Nov 6, 2025
  • scribe-task-suite Public

    A suite of interpretability tasks to evaluate agents using Scribe for notebook access

    goodfire-ai/scribe-task-suite’s past year of commit activity
    Jupyter Notebook 15 2 0 0 Updated Oct 2, 2025
  • goodfire-ai/hackathon-gpt-oss-interpretability’s past year of commit activity
    Jupyter Notebook 8 MIT 3 0 0 Updated Aug 8, 2025
  • goodfire-sdk Public archive

    Ember is a hosted API/SDK that lets you shape AI model behavior by directly controlling a model's internal units of computation, or "features". With Ember, you can modify features to precisely control model outputs, or use them as building blocks for tasks like classification.

    goodfire-ai/goodfire-sdk’s past year of commit activity
    Python 41 Apache-2.0 8 1 1 Updated Jul 14, 2025
  • goodfire-ai/sdxl-turbo-interpretability’s past year of commit activity
    Jupyter Notebook 47 MIT 6 0 0 Updated May 27, 2025
  • r1-interpretability Public

    Open source interpretability artefacts for R1.

    goodfire-ai/r1-interpretability’s past year of commit activity
    Jupyter Notebook 169 MIT 10 0 0 Updated Apr 21, 2025

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…