DevInterp is a python library for conducting research on developmental interpretability, a novel AI safety research agenda rooted in Singular Learning Theory (SLT). DevInterp proposes tools for detecting, locating, and ultimately controlling the development of structure over training.
Read more about developmental interpretability.
⚠️ This library is still in early development. Don't expect things to work on a first attempt. We are actively working on improving the library and adding new features. If you have any questions or suggestions, please feel free to open an issue or submit a pull request.
To install devinterp
, simply run:
pip install devinterp
Requirements: Python 3.8 or higher.
To see DevInterp in action, check out our example notebooks:
from devinterp.slt import estimate_learning_coeff, estimate_learning_coeff_with_summary
from devinterp.optim import SGLD
# Assuming you have a PyTorch Module and DataLoader
learning_coeff = estimate_learning_coeff(model, trainloader, ...)
# If you want to see mean, std, and learning coeff estimate per chain
learning_coeff_summary = estimate_learning_coeff_with_summary(model, trainloader, ...)
See CONTRIBUTING.md for guidelines on how to contribute.