RSS

Neel Nanda

Karma: 6,559

I lead the DeepMind mechanistic interpretability team

A Prag­matic Vi­sion for Interpretability

Neel Nanda3 Dec 2025 9:20 UTC
9 points
0 comments1 min readEA link

How To Be­come A Mechanis­tic In­ter­pretabil­ity Researcher

Neel Nanda2 Sep 2025 23:38 UTC
31 points
0 comments55 min readEA link

Neel Nanda MATS Ap­pli­ca­tions Open (Due Aug 29)

Neel Nanda30 Jul 2025 0:55 UTC
20 points
0 comments7 min readEA link
(tinyurl.com)

Ad­vice for Send­ing Cold Mes­sages to Busy Peo­ple at EAG

Neel Nanda2 Jun 2025 21:12 UTC
118 points
0 comments5 min readEA link

So­cratic Per­sua­sion: Giv­ing Opinionated Yet Truth-Seek­ing Advice

Neel Nanda26 May 2025 17:38 UTC
66 points
3 comments21 min readEA link
(www.neelnanda.io)

Highly Opinionated Ad­vice on How to Write ML Papers

Neel Nanda12 May 2025 1:59 UTC
22 points
0 comments32 min readEA link

In­ter­pretabil­ity Will Not Reli­ably Find De­cep­tive AI

Neel Nanda4 May 2025 16:32 UTC
74 points
0 comments7 min readEA link

My Re­search Pro­cess: Un­der­stand­ing and Cul­ti­vat­ing Re­search Taste

Neel Nanda1 May 2025 23:08 UTC
9 points
1 comment9 min readEA link

My Re­search Pro­cess: Key Mind­sets—Truth-Seek­ing, Pri­ori­ti­sa­tion, Mov­ing Fast

Neel Nanda27 Apr 2025 14:38 UTC
36 points
1 comment11 min readEA link

How I Think About My Re­search Pro­cess: Ex­plore, Un­der­stand, Distill

Neel Nanda26 Apr 2025 10:31 UTC
45 points
2 comments8 min readEA link

Neel Nanda’s Quick takes

Neel Nanda6 Apr 2025 22:17 UTC
8 points
3 commentsEA link

Good Re­search Takes are Not Suffi­cient for Good Strate­gic Takes

Neel Nanda22 Mar 2025 10:13 UTC
120 points
0 comments4 min readEA link
(www.neelnanda.io)

The GDM AGI Safety+Align­ment Team is Hiring for Ap­plied In­ter­pretabil­ity Research

Arthur Conmy25 Feb 2025 22:38 UTC
11 points
0 comments7 min readEA link

MATS Ap­pli­ca­tions + Re­search Direc­tions I’m Cur­rently Ex­cited About

Neel Nanda6 Feb 2025 11:03 UTC
31 points
3 comments8 min readEA link

Con­crete open prob­lems in mechanis­tic in­ter­pretabil­ity: a tech­ni­cal overview

Neel Nanda6 Jul 2023 11:35 UTC
27 points
1 comment29 min readEA link

Con­crete Steps to Get Started in Trans­former Mechanis­tic Interpretability

Neel Nanda26 Dec 2022 13:00 UTC
18 points
0 comments12 min readEA link

A Bare­bones Guide to Mechanis­tic In­ter­pretabil­ity Prerequisites

Neel Nanda29 Nov 2022 18:43 UTC
54 points
1 comment3 min readEA link
(neelnanda.io)

An Ex­tremely Opinionated An­no­tated List of My Favourite Mechanis­tic In­ter­pretabil­ity Papers

Neel Nanda18 Oct 2022 21:23 UTC
19 points
0 comments12 min readEA link
(www.neelnanda.io)

Con­crete Ad­vice for Form­ing In­side Views on AI Safety

Neel Nanda17 Aug 2022 23:26 UTC
58 points
4 comments10 min readEA link
(www.alignmentforum.org)

Things That Make Me En­joy Giv­ing Ca­reer Advice

Neel Nanda17 Jun 2022 20:49 UTC
33 points
3 comments9 min readEA link