SAEs for deep-ignorance-unfiltered (expansion factor 8, all layers)

Sparse autoencoders trained on all 32 layers of EleutherAI/deep-ignorance-unfiltered using the WMDP-Bio-Remove-Dataset.

Trained with EleutherAI/sparsify.

Training hyperparameters

Parameter Value
expansion_factor 8
k 32
layers all 32 (0-31)
batch_size 4
grad_acc_steps 8
micro_acc_steps 2
ctx_len 2048
optimizer signum
loss_fn fvu
activation topk
distributed distribute_modules across 4x GH200 120GB

Dataset

Unlearning/WMDP-Bio-Remove-Dataset (24,453 examples)

Usage

from sparsify import Sae

sae = Sae.load_from_hub("EleutherAI/sae-deep-ignorance-unfiltered-ex8", hookpoint="layers.10")

# Or load all layers
saes = Sae.load_many("EleutherAI/sae-deep-ignorance-unfiltered-ex8")
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for EleutherAI/sae-deep-ignorance-unfiltered-ex8

Unable to build the model tree, the base model loops to the model itself. Learn more.