polysemanticity

Here is 1 public repository matching this topic...

DeepCogNeural / mech-interp-lab

Reproducible toy-model experiments in mechanistic interpretability. Includes a test of whether mixed (superposed) coding is what lets a linear readout see feature interactions — headline result plus a reported null.

pytorch computational-neuroscience superposition ai-safety interpretability toy-models neuroai mechanistic-interpretability polysemanticity mixed-selectivity

Updated Aug 9, 2026
Python

Improve this page

Add a description, image, and links to the polysemanticity 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 polysemanticity topic, visit your repo's landing page and select "manage topics."

Learn more