RSS

Tom Lieberum

Karma: 964

Research Engineer at DeepMind, focused on mechanistic interpretability and large language models. Opinions are my own.

Nega­tive Re­sults for SAEs On Down­stream Tasks and Depri­ori­tis­ing SAE Re­search (GDM Mech In­terp Team Progress Up­date #2)

Mar 26, 2025, 7:07 PM
111 points
15 comments29 min readLW link
(deepmindsafetyresearch.medium.com)

JumpReLU SAEs + Early Ac­cess to Gemma 2 SAEs

Jul 19, 2024, 4:10 PM
48 points
10 comments1 min readLW link
(storage.googleapis.com)

Im­prov­ing Dic­tionary Learn­ing with Gated Sparse Autoencoders

Apr 25, 2024, 6:43 PM
63 points
38 comments1 min readLW link
(arxiv.org)

[Full Post] Progress Up­date #1 from the GDM Mech In­terp Team

Apr 19, 2024, 7:06 PM
79 points
10 comments8 min readLW link

[Sum­mary] Progress Up­date #1 from the GDM Mech In­terp Team

Apr 19, 2024, 7:06 PM
72 points
0 comments3 min readLW link

AtP*: An effi­cient and scal­able method for lo­cal­iz­ing LLM be­havi­our to components

Mar 18, 2024, 5:28 PM
19 points
0 comments1 min readLW link
(arxiv.org)

Does Cir­cuit Anal­y­sis In­ter­pretabil­ity Scale? Ev­i­dence from Mul­ti­ple Choice Ca­pa­bil­ities in Chinchilla

Jul 20, 2023, 10:50 AM
44 points
3 comments2 min readLW link
(arxiv.org)

A Mechanis­tic In­ter­pretabil­ity Anal­y­sis of Grokking

Aug 15, 2022, 2:41 AM
373 points
48 comments36 min readLW link1 review
(colab.research.google.com)

In­ves­ti­gat­ing causal un­der­stand­ing in LLMs

Jun 14, 2022, 1:57 PM
28 points
6 comments13 min readLW link

Thoughts on For­mal­iz­ing Composition

Tom LieberumJun 7, 2022, 7:51 AM
13 points
0 comments7 min readLW link

Un­der­stand­ing the ten­sor product for­mu­la­tion in Trans­former Circuits

Tom LieberumDec 24, 2021, 6:05 PM
16 points
2 comments3 min readLW link

[Question] How should my timelines in­fluence my ca­reer choice?

Tom LieberumAug 3, 2021, 10:14 AM
13 points
10 comments1 min readLW link