Transformers
sae
sparse-autoencoder
t5gemma
t5gemma2
mechanistic-interpretability
activation-steering
steering
neuronpedia
gemma-scope
sae-lens
llm-interpretability
explainable-ai
xai
model-steering
feature-engineering
representation-learning
Instructions to use mindchain/t5gemma2-sae-all-layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mindchain/t5gemma2-sae-all-layers with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mindchain/t5gemma2-sae-all-layers", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download encoder/sae_encoder_00.pt from mindchain/t5gemma2-sae-all-layers: direct link, hf CLI and curl.
- Browser
- Download file 21 MB
-
https://huggingface.co/mindchain/t5gemma2-sae-all-layers/resolve/main/encoder/sae_encoder_00.pt
- Command line
-
hf download hf://mindchain/t5gemma2-sae-all-layers/encoder/sae_encoder_00.pt
-
curl -L -o sae_encoder_00.pt https://huggingface.co/mindchain/t5gemma2-sae-all-layers/resolve/main/encoder/sae_encoder_00.pt
21 MB
- Xet hash:
- b67e621b5aebc4151304c21545af0f6e4a2948d586a4bddcaba4cde2fe35d888
- Size of remote file:
- 21 MB
- SHA256:
- 414e9f673caf7b3d42938325e7d468d52312ec7d82c4c2d2a8e92d92f533e571
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.