Kavli Affiliate: Max Tegmark
| First 5 Authors: Matthew Chen, Joshua Engels, Max Tegmark, ,
| Summary:
Sparse autoencoders (SAEs) decompose language model representations into a
sparse set of linear latent vectors. Recent works have improved SAEs using
language model gradients, but these techniques require many expensive backward
passes during training and still cause a significant increase in cross entropy
loss when SAE reconstructions are inserted into the model. In this work, we
improve on these limitations by taking a fundamentally different approach: we
use low-rank adaptation (LoRA) to finetune the language model itself around a
previously trained SAE. We analyze our method across SAE sparsity, SAE width,
language model size, LoRA rank, and model layer on the Gemma Scope family of
SAEs. In these settings, our method reduces the cross entropy loss gap by 30%
to 55% when SAEs are inserted during the forward pass. We also find that
compared to end-to-end (e2e) SAEs, our approach achieves the same downstream
cross entropy loss 3$times$ to 20$times$ faster on Gemma-2-2B and 2$times$
to 10$times$ faster on Llama-3.2-1B. We further show that our technique
improves downstream metrics and can adapt multiple SAEs at once. Our results
demonstrate that improving model interpretability is not limited to post-hoc
SAE training; Pareto improvements can also be achieved by directly optimizing
the model itself.
| Search Query: ArXiv Query: search_query=au:”Max Tegmark”&id_list=&start=0&max_results=3