Downloads · 30 days
9
25% of all-time downloads
YusongZhao666/csae-ckpt
csae-ckpt is a feature extraction model from YusongZhao666. Use it when you need embeddings to search or compare text. The card lists the license as mit.
This repository contains a trained checkpoint of the SAE++ model introduced in the paper SAE++: Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs.
Downloads · 30 days
9
25% of all-time downloads
All-time downloads
36
Public
Repo size
246 MB
Likes
0
Public
Click a slice to open those files.
.pt246 MB · 100%
From the Hugging Face model README
This repository contains a trained checkpoint of the SAE++ model introduced in the paper SAE++: Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs.
SAE++ is a cascaded sparse autoencoder architecture that learns multi-level visual concepts from MLLM activations. The Level-1 SAE recovers fine-grained concepts, and a Level-2 SAE is trained directly on the Level-1 decoder weights to learn higher-level "concepts of concepts." This improves hierarchical interpretability and enables group-level steering of MLLM outputs.
For usage, training scripts, evaluation, and steering demos, please refer to the official code repository: https://github.com/Wang-ML-Lab/sae-plus-plus.