RSS

Lee Sharkey(Lee Sharkey)

Karma: 739

Research engineer at Apollo Research (London).

My main research interests are mechanistic interpretability and inner alignment.

An­nounc­ing Apollo Research

30 May 2023 16:17 UTC
201 points
8 comments8 min readLW link

‘Fun­da­men­tal’ vs ‘ap­plied’ mechanis­tic in­ter­pretabil­ity research

Lee Sharkey23 May 2023 18:26 UTC
59 points
6 comments3 min readLW link

A tech­ni­cal note on bil­in­ear lay­ers for interpretability

Lee Sharkey8 May 2023 6:06 UTC
50 points
0 comments1 min readLW link
(arxiv.org)

A small up­date to the Sparse Cod­ing in­terim re­search report

30 Apr 2023 19:54 UTC
60 points
5 comments1 min readLW link

Why al­most ev­ery RL agent does learned optimization

Lee Sharkey12 Feb 2023 4:58 UTC
32 points
3 comments5 min readLW link

[In­terim re­search re­port] Tak­ing fea­tures out of su­per­po­si­tion with sparse autoencoders

13 Dec 2022 15:41 UTC
92 points
14 comments22 min readLW link

Cur­rent themes in mechanis­tic in­ter­pretabil­ity research

16 Nov 2022 14:14 UTC
87 points
3 comments12 min readLW link

In­ter­pret­ing Neu­ral Net­works through the Poly­tope Lens

23 Sep 2022 17:58 UTC
132 points
29 comments33 min readLW link