Skip to content

@redwoodresearch Redwood Research

Change the repository type filter

All

    Repositories list

    15 repositories

    • alignment_faking_public

      Public
      Python
      •
      MIT License
      •7•21•0•0•Updated Dec 27, 2024Dec 27, 2024

    • alignment_faking_examples

      Public
      2•3•0•0•Updated Dec 25, 2024Dec 25, 2024

    • Easy-Transformer

      Public
      Python
      •
      MIT License
      •314•104•0•0•Updated Aug 4, 2024Aug 4, 2024

    • Text-Steganography-Benchmark

      Public
      Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.
      Python
      •4•14•0•0•Updated Jan 26, 2024Jan 26, 2024

    • Gradient-Machine

      Public
      Python
      •1•0•0•0•Updated Oct 20, 2023Oct 20, 2023

    • Measurement-Tampering

      Public
      Evaluation of measurement tampering detection techniques on the datasets from Benchmarks for Detecting Measurement Tampering
      Python
      •
      MIT License
      •3•4•0•0•Updated Sep 7, 2023Sep 7, 2023

    • cumulant_decomposition

      Public
      Python
      •1•0•0•0•Updated Apr 18, 2023Apr 18, 2023

    • pyo3

      Public
      Rust bindings for the Python interpreter
      Rust
      •
      Other
      •782•0•0•0•Updated Apr 11, 2023Apr 11, 2023

    • remix_public

      Public
      Python
      •3•19•1•0•Updated Feb 17, 2023Feb 17, 2023

    • rust_circuit_public

      Public
      Rust
      •
      MIT License
      •2•61•1•0•Updated Feb 16, 2023Feb 16, 2023

    • maturin

      Public
      Build and publish crates with pyo3, rust-cpython and cffi bindings as well as rust binaries as python packages
      Rust
      •
      Apache License 2.0
      •279•0•0•0•Updated Nov 11, 2022Nov 11, 2022

    • hypothesis

      Public
      Hypothesis is a powerful, flexible, and easy to use library for property-based testing.
      Python
      •
      Other
      •588•0•0•0•Updated Sep 28, 2022Sep 28, 2022

    • mlab

      Public
      Machine Learning for Alignment Bootcamp
      Jupyter Notebook
      •41•68•2•3•Updated Apr 27, 2022Apr 27, 2022

    • jaxtyping

      Public
      Type annotations for Jax arrays. Fork of torchtyping.
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Apr 27, 2022Apr 27, 2022

    • interp

      Public
      Redwood Research's transformer interpretability tools
      TypeScript
      •
      MIT License
      •0•12•0•0•Updated Apr 15, 2022Apr 15, 2022