staircase SAEs
Collection
5 items • Updated
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
The proposed Staircase SAE architecture using Top- K activation, as described in Section 3. The total number of features N = n × (L + 1) was chosen such that the total parameter count is comparable to the Topk and Topk-Staircase-Tied-All models.
This is what you want if you want the staircase model. Use this one.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support