eleutherai interpretability reading group 220226: locating and editing factual knowledge in gpt
Published 2 years ago • 1.2K plays • Length 1:20:22Download video MP4
Download video MP3
Similar videos
-
1:04:59
rome: locating and editing factual associations in gpt (paper explained & author interview)
-
1:05:45
eleutherai interpretability reading group 220604: attention head bandwidth connectomes of llms.
-
3:14
editing factual associations in gpt with rome
-
1:00:25
talk by francoise tisseur (university of manchester)
-
12:17
the digital maturity dilemma | alvaro arenas | tedxiemadrid
-
1:06:56
large language models and the end of programming - cs50 tech talk with dr. matt welsh
-
42:10
[2021 microsoft ] lora: low-rank adaptation of large language models
-
1:00:31
talk "towards network structured lasserre hierarchy for stability analysis" by matteo tacchi (epfl)
-
30:11
rémi eyraud: tassil/taysir: upcoming competition: extracting simple models from rnns & transformers
-
0:39
assisted lithology interpretation – data validation
-
4:29
unlocking the mystery: what large language models can't do (yet)
-
55:51
meta-forum 2023: session 4: european large language models
-
14:20
university of toronto: human creativity in the age of llms
-
29:19
enlit europe - datatopia podcast - episode 2 - lora alliance
-
2:21
eit label compilation
-
21:24
prof. dr. andrés quero, "meister eckhart & schelling on the bounds of love" leeds, uk, 4/7/2022