Archive
About
Search
Log In
Home
All
Wiki
Shortform
Recent
Comments
RSS
Neel Nanda
Karma:
6,559
I lead the DeepMind mechanistic interpretability team
All
Posts
Comments
New
Top
Old
Page
1
A Pragmatic Vision for Interpretability
Neel Nanda
3 Dec 2025 9:20 UTC
9
points
0
comments
1
min read
EA
link
How To Become A Mechanistic Interpretability Researcher
Neel Nanda
2 Sep 2025 23:38 UTC
31
points
0
comments
55
min read
EA
link
Neel Nanda MATS Applications Open (Due Aug 29)
Neel Nanda
30 Jul 2025 0:55 UTC
20
points
0
comments
7
min read
EA
link
(tinyurl.com)
Advice for Sending Cold Messages to Busy People at EAG
Neel Nanda
2 Jun 2025 21:12 UTC
118
points
0
comments
5
min read
EA
link
Socratic Persuasion: Giving Opinionated Yet Truth-Seeking Advice
Neel Nanda
26 May 2025 17:38 UTC
66
points
3
comments
21
min read
EA
link
(www.neelnanda.io)
Highly Opinionated Advice on How to Write ML Papers
Neel Nanda
12 May 2025 1:59 UTC
22
points
0
comments
32
min read
EA
link
Interpretability Will Not Reliably Find Deceptive AI
Neel Nanda
4 May 2025 16:32 UTC
74
points
0
comments
7
min read
EA
link
My Research Process: Understanding and Cultivating Research Taste
Neel Nanda
1 May 2025 23:08 UTC
9
points
1
comment
9
min read
EA
link
My Research Process: Key Mindsets—Truth-Seeking, Prioritisation, Moving Fast
Neel Nanda
27 Apr 2025 14:38 UTC
36
points
1
comment
11
min read
EA
link
How I Think About My Research Process: Explore, Understand, Distill
Neel Nanda
26 Apr 2025 10:31 UTC
45
points
2
comments
8
min read
EA
link
Neel Nanda’s Quick takes
Neel Nanda
6 Apr 2025 22:17 UTC
8
points
3
comments
EA
link
Good Research Takes are Not Sufficient for Good Strategic Takes
Neel Nanda
22 Mar 2025 10:13 UTC
120
points
0
comments
4
min read
EA
link
(www.neelnanda.io)
The GDM AGI Safety+Alignment Team is Hiring for Applied Interpretability Research
Arthur Conmy
25 Feb 2025 22:38 UTC
11
points
0
comments
7
min read
EA
link
MATS Applications + Research Directions I’m Currently Excited About
Neel Nanda
6 Feb 2025 11:03 UTC
31
points
3
comments
8
min read
EA
link
Concrete open problems in mechanistic interpretability: a technical overview
Neel Nanda
6 Jul 2023 11:35 UTC
27
points
1
comment
29
min read
EA
link
Concrete Steps to Get Started in Transformer Mechanistic Interpretability
Neel Nanda
26 Dec 2022 13:00 UTC
18
points
0
comments
12
min read
EA
link
A Barebones Guide to Mechanistic Interpretability Prerequisites
Neel Nanda
29 Nov 2022 18:43 UTC
54
points
1
comment
3
min read
EA
link
(neelnanda.io)
An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers
Neel Nanda
18 Oct 2022 21:23 UTC
19
points
0
comments
12
min read
EA
link
(www.neelnanda.io)
Concrete Advice for Forming Inside Views on AI Safety
Neel Nanda
17 Aug 2022 23:26 UTC
58
points
4
comments
10
min read
EA
link
(www.alignmentforum.org)
Things That Make Me Enjoy Giving Career Advice
Neel Nanda
17 Jun 2022 20:49 UTC
33
points
3
comments
9
min read
EA
link
Back to top
Next