Comment by Adly Templeton (adly-templeton-1) on I am the Golden Gate Bridge · 2024-05-27T23:10:55.200Z · LW · GW

If you scroll down on the Feature Catalog (https://transformer-circuits.pub/2024/scaling-monosemanticity/features/index.html?featureId=1M_120374) you can view 1,000 randomly selected features from each run.  This is a great way to get a sense for the average interpretability of features.