Event Dime
SAE It Across Models: Explaining Features With Foreign NLA Verbalizers
- When:
- June 5, 2026 · 6:36 PM
- Where:
- A review of Where Is My Flying Car? by J. Storrs Hall — LessWrong
- Source:
- A review of Where Is My Flying Car? by J. Storrs Hall — LessWrong
TLDR: I show that a foreign model's Natural Language Autoencoder (NLA) Activation Verbalizer (AV) can produce plausible explanations for SAE features from a model it was never trained on. It is currently assumed that these tools only work for the exact model and layer they were trained for. I show that is not the case. After creating a ridge-regression map bridging the residual stream of Qwen2.5-7B-IT at layer 20 and Gemma-3-27B-IT at layer 41, I mapped 45 SAE decoder directions from a Qwen SAE