mech-interp

Implementation and analysis of Sparse Autoencoders for neural network interpretability research. Features interactive visualization dashboard and W&B integration.

sparse-autoencoders interpretability activation-functions neuron-activity wandb transformerlens mech-interp

Updated May 17, 2025
Python

ashioyajotham / interp

Star

My AI interpretability research journey

backpropagation sparse-autoencoders interpretability mech-interp

Updated Feb 21, 2025
HTML

Improve this page

Add a description, image, and links to the mech-interp topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the mech-interp topic, visit your repo's landing page and select "manage topics."

Learn more

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

mech-interp

Here are 6 public repositories matching this topic...

codelion / pts

ky295 / adv-steer

coderinblack08 / prompt-helmet

1289nav / Exploring-chain-of-thought-reasoning-in-LLMs

ashioyajotham / exploring_saes

ashioyajotham / interp

Improve this page

Add this topic to your repo