redwoodresearch Goto Github PK

cumulant_decomposition

easy-transformer

gradient-machine

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.

maturin

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

measurement-tampering

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

mlab

Machine Learning for Alignment Bootcamp

pyo3

Rust bindings for the Python interpreter

remix_public

rust_circuit_public

text-steganography-benchmark

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