Redwood Research

cumulant_decomposition

Easy-Transformer

hypothesis

Hypothesis is a powerful, flexible, and easy to use library for property-based testing.

interp

Redwood Research's transformer interpretability tools

jaxtyping

Type annotations for Jax arrays. Fork of torchtyping.

Measurement-Tampering

Evaluation of measurement tampering detection techniques on the datasets from Benchmarks for Detecting Measurement Tampering

mlab

Machine Learning for Alignment Bootcamp

remix_public

rust_circuit_public

Text-Steganography-Benchmark

Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.

redwoodresearch/Easy-Transformer

redwoodresearch/mlab

Machine Learning for Alignment Bootcamp

redwoodresearch/rust_circuit_public

redwoodresearch/remix_public

redwoodresearch/Text-Steganography-Benchmark

Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.

redwoodresearch/interp

Redwood Research's transformer interpretability tools

redwoodresearch/Measurement-Tampering

Evaluation of measurement tampering detection techniques on the datasets from Benchmarks for Detecting Measurement Tampering

redwoodresearch/cumulant_decomposition

redwoodresearch/hypothesis

Hypothesis is a powerful, flexible, and easy to use library for property-based testing.

redwoodresearch/jaxtyping

Type annotations for Jax arrays. Fork of torchtyping.

redwoodresearch/Gradient-Machine

redwoodresearch/maturin

Build and publish crates with pyo3, rust-cpython and cffi bindings as well as rust binaries as python packages

redwoodresearch/pyo3

Rust bindings for the Python interpreter