Downloads · 30 days
0
ace-step-sae-tf7-cross-attn
lukasz-staniszewski/ace-step-sae-tf7-cross-attn
ace-step-sae-tf7-cross-attn is a machine learning model from lukasz-staniszewski. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for audio-interv.
Sparse autoencoder trained on ACE-Step cross-attention activations.
Access
Public
Updated May 26, 2026
Repo size
210 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors210 MB · 100%
At a glance
- Library
- audio-interv
- Access
- Public
- Created
- May 19, 2026
- Updated
- May 26, 2026
- SHA
- 8843d555
Model card
From the Hugging Face model README
SAE — ACE-Step (transformer_blocks.7.cross_attn)
Sparse autoencoder trained on ACE-Step cross-attention activations.
Paper
TADA! Tuning Audio Diffusion Models through Activation Steering — https://huggingface.co/papers/2602.11910
Quickstart
from src.steering.methods.sae.lib.sae.sae import Sae
sae = Sae.load_from_hub(
"lukasz-staniszewski/ace-step-sae-tf7-cross-attn",
hookpoint="transformer_blocks.7.cross_attn", device="cuda",
)
- Library
- audio-interv
- Created
- May 19, 2026
- Updated
- May 26, 2026