Adrià Garriga-alonso

Karma: 1,227

Sparsity is the enemy of feature extraction (ft. absorption)

7vik, chanind and Adrià Garriga-alonso

May 3, 2025, 10:13 AM

31 points

0 comments6 min readLW link

Among Us: A Sandbox for Agentic Deception

7vik and Adrià Garriga-alonso

Apr 5, 2025, 6:24 AM

110 points

7 comments7 min readLW link

A Bunch of Matryoshka SAEs

chanind, TomasD and Adrià Garriga-alonso

Apr 4, 2025, 2:53 PM

24 points

0 comments8 min readLW link

Feature Hedging: Another way correlated features break SAEs

chanind, TomasD and Adrià Garriga-alonso

Mar 25, 2025, 2:33 PM

22 points

0 comments18 min readLW link

Illusory Safety: Redteaming DeepSeek R1 and the Strongest Fine-Tunable Models of OpenAI, Anthropic, and Google

ChengCheng, Brendan Murphy, Adrià Garriga-alonso, Yashvardhan Sharma, dsbowen, smallsilo, Yawen Duan, ChrisCundy, Hannah Betts, AdamGleave and Kellin Pelrine

Feb 7, 2025, 3:57 AM

29 points

0 comments10 min readLW link

Crafting Polysemantic Transformer Benchmarks with Known Circuits

Evan Anders and Adrià Garriga-alonso

Aug 23, 2024, 10:03 PM

17 points

0 comments25 min readLW link

Pacing Outside the Box: RNNs Learn to Plan in Sokoban

Adrià Garriga-alonso, taufeeque, AdamGleave and ChengCheng

Jul 25, 2024, 10:00 PM

59 points

8 comments2 min readLW link

(arxiv.org)

Compact Proofs of Model Performance via Mechanistic Interpretability

LawrenceC, rajashree, Adrià Garriga-alonso and Jason Gross

Jun 24, 2024, 7:27 PM

96 points

4 comments8 min readLW link

(arxiv.org)

Catastrophic Goodhart in RL with KL penalty

Thomas Kwa and Adrià Garriga-alonso

May 15, 2024, 12:58 AM

62 points

10 comments7 min readLW link

An evaluation of circuit evaluation metrics

Iván Arcuschin, Niels uit de Bos and Adrià Garriga-alonso

Apr 15, 2024, 7:38 PM

18 points

0 comments4 min readLW link

Ophiology (or, how the Mamba architecture works)

Danielle Ensign, SrGonao and Adrià Garriga-alonso

Apr 9, 2024, 7:31 PM

67 points

8 comments10 min readLW link

Does literacy remove your ability to be a bard as good as Homer?

Adrià Garriga-alonsoJan 18, 2024, 3:43 AM

51 points

19 comments3 min readLW link

Thomas Kwa’s research journal

Thomas Kwa and Adrià Garriga-alonso

Nov 23, 2023, 5:11 AM

79 points

1 comment6 min readLW link

On Frequentism and Bayesian Dogma

DanielFilan and Adrià Garriga-alonso

Oct 15, 2023, 10:23 PM

59 points

27 comments6 min readLW link

A comparison of causal scrubbing, causal abstractions, and related methods

Erik Jenner, Adrià Garriga-alonso and Egor Zverev

Jun 8, 2023, 11:40 PM

73 points

3 comments22 min readLW link

Causal scrubbing: results on induction heads

LawrenceC, Adrià Garriga-alonso, Nicholas Goldowsky-Dill, ryan_greenblatt, Tao Lin, jenny, Ansh Radhakrishnan, Buck and Nate Thomas

Dec 3, 2022, 12:59 AM

34 points

1 comment17 min readLW link

Causal scrubbing: results on a paren balance checker

LawrenceC, Adrià Garriga-alonso, Nicholas Goldowsky-Dill, ryan_greenblatt, Tao Lin, jenny, Ansh Radhakrishnan, Buck and Nate Thomas

Dec 3, 2022, 12:59 AM

34 points

2 comments30 min readLW link

Causal scrubbing: Appendix

LawrenceC, Adrià Garriga-alonso, Nicholas Goldowsky-Dill, ryan_greenblatt, jenny, Ansh Radhakrishnan, Buck and Nate Thomas

Dec 3, 2022, 12:58 AM

18 points

4 comments20 min readLW link

Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]

LawrenceC, Adrià Garriga-alonso, Nicholas Goldowsky-Dill, ryan_greenblatt, jenny, Ansh Radhakrishnan, Buck and Nate Thomas

Dec 3, 2022, 12:58 AM

206 points

35 comments20 min readLW link 1 review

The No Free Lunch theorems and their Razor

Adrià Garriga-alonsoMay 24, 2022, 6:40 AM

56 points

3 comments9 min readLW link

Keyboard shortcuts

Keys shown in yellow (e.g., ]) are accesskeys, and require a browser-specific modifier key (or keys).

Keys shown in grey (e.g., ?) do not require any modifier keys.

General
? Show keyboard shortcuts
Esc Hide keyboard shortcuts

Site navigation
h Go to Home (a.k.a. “Frontpage”) view
f Go to Featured (a.k.a. “Curated”) view
a Go to All (a.k.a. “Community”) view
m Go to Meta view
v Go to Tags view
c Go to Recent Comments view
r Go to Archive view
q Go to Sequences view
t Go to About page
u Go to User or Login page
o Go to Inbox page

Page navigation
, Jump up to top of page
. Jump down to bottom of page
/ Jump to top of comments section
s Search

Page actions
n New post or comment
e Edit current post

Post/comment list views
. Focus next entry in list
, Focus previous entry in list
; Cycle between links in focused entry
Enter Go to currently focused entry
Esc Unfocus currently focused entry
] Go to next page
[ Go to previous page
\ Go to first page
e Edit currently focused post

Editor
k Bold text
i Italic text
l Insert hyperlink
q Blockquote text

Appearance
= Increase text size
- Decrease text size
0 Reset to default text size
′ Cycle through content width settings
1 Switch to default theme [A]
2 Switch to dark theme [B]
3 Switch to grey theme [C]
4 Switch to ultramodern theme [D]
5 Switch to simple theme [E]
6 Switch to brutalist theme [F]
7 Switch to ReadTheSequences theme [G]
8 Switch to classic Less Wrong theme [H]
9 Switch to modern Less Wrong theme [I]
; Open theme tweaker
Enter Save changes and close theme tweaker
Esc Close theme tweaker (without saving)

Slide shows
l Start/resume slideshow
Esc Exit slideshow
→↓ Next slide
←↑ Previous slide
Space Reset slide zoom

Miscellaneous
x Switch to next view on user page
z Switch to previous view on user page
` Toggle compact comment list view
g Toggle anti-kibitzer