RSS

MadHatter

Karma: 359

“We are computer scientists. We do not lack in faith.” (Ketan Mulmuley)

A mechanis­tic ex­pla­na­tion for SolidGoldMag­ikarp-like to­kens in GPT2

MadHatterFeb 26, 2023, 1:10 AM
61 points
14 comments6 min readLW link

In­ter­ven­ing in the Resi­d­ual Stream

MadHatterFeb 22, 2023, 6:29 AM
30 points
1 comment9 min readLW link

Is AI Gain-of-Func­tion re­search a thing?

MadHatterNov 12, 2022, 2:33 AM
9 points
2 comments2 min readLW link

Try­ing to Make a Treach­er­ous Mesa-Optimizer

MadHatterNov 9, 2022, 6:07 PM
95 points
14 comments4 min readLW link
(attentionspan.blog)

Mechanis­tic In­ter­pretabil­ity for the MLP Lay­ers (rough early thoughts)

MadHatterDec 24, 2021, 7:24 AM
12 points
3 comments1 min readLW link
(www.youtube.com)

Hard-Cod­ing Neu­ral Computation

MadHatterDec 13, 2021, 4:35 AM
34 points
8 comments27 min readLW link

Teaser: Hard-cod­ing Trans­former Models

MadHatterDec 12, 2021, 10:04 PM
74 points
19 comments1 min readLW link