Single SAEs trained on the residual stream activation vectors from every transformer layer simultaneously: https://arxiv.org/abs/2409.04185
Tim Lawson
tim-lawson
·
AI & ML interests
Mechanistic interpretability, language modelling, semantics
Recent Activity
updated
a model
1 day ago
tim-lawson/1c81f4e8-a72d-4bbf-bbf7-39f3f0880c29
updated
a model
1 day ago
tim-lawson/62c023f5-fe83-487b-8b95-1c8bacd505bf
updated
a model
1 day ago
tim-lawson/01f98b06-e240-4115-b2da-ba68f32e8bac
Organizations
None yet
Collections
6
Papers
1
models
289

tim-lawson/1c81f4e8-a72d-4bbf-bbf7-39f3f0880c29
Updated
•
6

tim-lawson/62c023f5-fe83-487b-8b95-1c8bacd505bf
Updated
•
4

tim-lawson/01f98b06-e240-4115-b2da-ba68f32e8bac
Updated
•
4

tim-lawson/mlsae-gemma-2-2b-x64-k32
Updated
•
26

tim-lawson/mlsae-gemma-2-2b-x64-k32-tfm
Updated
•
23

tim-lawson/mlsae-Llama-3.2-3B-x64-k32
Updated
•
13

tim-lawson/mlsae-Llama-3.2-3B-x64-k32-tfm
Updated
•
27

tim-lawson/temp-pythia-70m-deduped-x64-k32-l3
Updated

tim-lawson/temp-pythia-160m-deduped-x64-k32-l2
Updated

tim-lawson/temp-pythia-160m-deduped-x64-k32-l0
Updated
datasets
61
tim-lawson/mlsae-pythia-1.4b-deduped-x64-k32-dists
Viewer
•
Updated
•
131k
•
46
tim-lawson/mlsae-Llama-3.2-3B-x64-k32-dists
Viewer
•
Updated
•
197k
•
56
tim-lawson/mlsae-gemma-2-2b-x64-k32-dists
Viewer
•
Updated
•
147k
•
54
tim-lawson/mlsae-gpt2-x64-k32-dists
Preview
•
Updated
•
42
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-11-dists
Viewer
•
Updated
•
49.2k
•
39
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-10-dists
Viewer
•
Updated
•
49.2k
•
41
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-8-dists
Viewer
•
Updated
•
49.2k
•
39
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-9-dists
Viewer
•
Updated
•
49.2k
•
41
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-7-dists
Viewer
•
Updated
•
49.2k
•
38
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-5-dists
Viewer
•
Updated
•
49.2k
•
40