Single-Layer SAEs with Transformers
Collection
TopK SAEs trained on the residual stream activation vectors from a single transformer layer, including the transformers.
•
43 items
•
Updated
Tim Lawson
tim-lawson
AI & ML interests
language models, interpretability
Recent Activity
updated
a collection
3 days ago
Single-Layer SAEs with Transformers
updated
a collection
3 days ago
Single-Layer SAEs
updated
a collection
3 days ago
Multi-Layer SAEs with Tuned Lens and Transformers
Organizations
None yet
updated
7
collections
3 days ago
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr
Add pipeline tag
#1 opened 3 days ago
by
nielsr