openai / automated-interpretability

977 stars 116 forks source link

About Direction Finding #12

Closed JiruiLiu closed 1 year ago

JiruiLiu commented 1 year ago

Dear authors, do you plan to open source the “Finding explainable directions” part of the code in the future? Thanks.

redknight99 commented 1 year ago

Sorry to bother, could you link to the "Finding explainable directions" part in the Repo? I would like to understand the question better. Thank you.

WuTheFWasThat commented 1 year ago

they are referring to https://openaipublic.blob.core.windows.net/neuron-explainer/paper/index.html#sec-direction-finding

we don't plan to open source this