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 dataset
1 day ago
tim-lawson/mlsae-Llama-3.2-3B-x64-k32-dists
updated
a dataset
1 day ago
tim-lawson/mlsae-gemma-2-2b-x64-k32-dists
updated
a model
1 day ago
tim-lawson/mlsae-gemma-2-2b-x64-k32
Organizations
None yet
Collections
6
Papers
1
models
191
tim-lawson/mlsae-gemma-2-2b-x64-k32
Updated
•
9
tim-lawson/mlsae-gemma-2-2b-x64-k32-tfm
Updated
•
24
tim-lawson/mlsae-Llama-3.2-3B-x64-k32
Updated
•
10
tim-lawson/mlsae-Llama-3.2-3B-x64-k32-tfm
Updated
•
29
tim-lawson/mlsae-pythia-1b-deduped-x64-k32-tfm
Updated
•
44
tim-lawson/mlsae-pythia-410m-deduped-x64-k32-tfm
Updated
•
52
tim-lawson/mlsae-pythia-160m-deduped-x64-k512-tfm
Updated
•
28
tim-lawson/mlsae-pythia-160m-deduped-x64-k256-tfm
Updated
•
28
tim-lawson/mlsae-pythia-160m-deduped-x64-k128-tfm
Updated
•
25
tim-lawson/mlsae-pythia-160m-deduped-x64-k64-tfm
Updated
•
31
datasets
60
tim-lawson/mlsae-Llama-3.2-3B-x64-k32-dists
Viewer
•
Updated
•
197k
•
38
tim-lawson/mlsae-gemma-2-2b-x64-k32-dists
Viewer
•
Updated
•
147k
•
42
tim-lawson/mlsae-gpt2-x64-k32-dists
Preview
•
Updated
•
32
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-11-dists
Viewer
•
Updated
•
49.2k
•
31
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-10-dists
Viewer
•
Updated
•
49.2k
•
34
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-8-dists
Viewer
•
Updated
•
49.2k
•
38
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-9-dists
Viewer
•
Updated
•
49.2k
•
31
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-7-dists
Viewer
•
Updated
•
49.2k
•
31
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-5-dists
Viewer
•
Updated
•
49.2k
•
31
tim-lawson/sae-pythia-160m-deduped-x64-k32-tfm-layers-6-dists
Viewer
•
Updated
•
49.2k
•
32