Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Solshine
/
deception-sae-nanochat-d20
like
1
deception-detection
sparse-autoencoders
mechanistic-interpretability
ai-safety
nanochat
arxiv:
2503.07683
License:
mit
Model card
Files
Files and versions
xet
Community
main
deception-sae-nanochat-d20
630 MB
Ctrl+K
Ctrl+K
1 contributor
History:
15 commits
Solshine
Upload training_results.json with huggingface_hub
7f8c164
verified
15 days ago
.gitattributes
Safe
1.52 kB
initial commit
15 days ago
README.md
2.87 kB
Upload README.md with huggingface_hub
15 days ago
d20_L10_deception_jumprelu.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L10_deception_jumprelu.pt with huggingface_hub
15 days ago
d20_L10_deception_topk.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L10_deception_topk.pt with huggingface_hub
15 days ago
d20_L10_honest_jumprelu.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L10_honest_jumprelu.pt with huggingface_hub
15 days ago
d20_L10_mixed_jumprelu.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L10_mixed_jumprelu.pt with huggingface_hub
15 days ago
d20_L10_standard_jumprelu.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L10_standard_jumprelu.pt with huggingface_hub
15 days ago
d20_L10_standard_topk.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L10_standard_topk.pt with huggingface_hub
15 days ago
d20_L18_deception_jumprelu.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L18_deception_jumprelu.pt with huggingface_hub
15 days ago
d20_L18_deception_topk.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L18_deception_topk.pt with huggingface_hub
15 days ago
d20_L18_honest_jumprelu.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L18_honest_jumprelu.pt with huggingface_hub
15 days ago
d20_L18_mixed_jumprelu.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L18_mixed_jumprelu.pt with huggingface_hub
15 days ago
d20_L18_standard_jumprelu.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L18_standard_jumprelu.pt with huggingface_hub
15 days ago
d20_L18_standard_topk.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
What is a pickle import?
52.5 MB
xet
Upload d20_L18_standard_topk.pt with huggingface_hub
15 days ago
training_results.json
6.8 kB
Upload training_results.json with huggingface_hub
15 days ago