Comment by Jatin Nainani (jatin-nainani) on Write Good Enough Code, Quickly · 2024-12-15T13:32:33.681Z · LW · GW

Can't agree more with this post! I used to be afraid of long notebooks but they are powerful in allowing me to just think. 

Although while creating a script I tend to use "#%%" of vscode to run cells inside the script to test stuff. My notebooks usually contain a bunch of analysis code that don't need to be run, but should stay. 

Comment by Jatin Nainani (jatin-nainani) on SAEs are highly dataset dependent: a case study on the refusal direction · 2024-11-10T21:16:18.033Z · LW · GW

Makes sense! Thanks! In that case, we can potentially reduce the width, which might (along with a smaller dataset) help scale saes to understanding mechanisms in big models? 

Comment by Jatin Nainani (jatin-nainani) on SAEs are highly dataset dependent: a case study on the refusal direction · 2024-11-07T23:38:32.449Z · LW · GW

Great work! Is there something like too narrow of a dataset? For refusal, what do you think happens if we specifically train on a bunch of examples that show signs refusal?