Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
connaaa
/
interpgpt-sae-phase5
like
0
sae_lens
interpretability
sparse-autoencoder
sae
mechanistic-interpretability
topk-sae
License:
mit
Model card
Files
Files and versions
xet
Community
main
interpgpt-sae-phase5
118 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
connaaa
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
5f2451e
verified
21 days ago
adhd_L1_hook_resid_post
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
adhd_L2_hook_resid_post
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
adhd_L3_hook_resid_post
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
standard_L0_hook_resid_post
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
standard_L1_hook_resid_post
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
standard_L2_hook_resid_post
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
standard_L3_hook_resid_post
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
.gitattributes
Safe
133 Bytes
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
README.md
2.35 kB
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
causal_nulls_per_seed.json
2.17 kB
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
deepdive_steering.json
7.52 kB
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
feature_diff.json
2.71 kB
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
loading_example.py
361 Bytes
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago
three_probes.json
1.98 kB
Phase 5 release: 7 TopK SAEs + specificity / null-steering JSON artifacts
21 days ago