8.93 GB

Ctrl+K

1 contributor

History: 1 commit

Solshine

Initial public release: SAE weights, cfg, and model card

d453b54 about 1 month ago

d32_gated_L12_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L12_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L12_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L16_control
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L16_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L16_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L16_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L20_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L20_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L20_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L24_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L24_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L24_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L4_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L4_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L4_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L8_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L8_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_gated_L8_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L12_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L12_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L12_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L16_control
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L16_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L16_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L16_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L20_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L20_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L20_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L24_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L24_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L24_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L4_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L4_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L4_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L8_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L8_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_jumprelu_L8_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L12_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L12_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L12_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L16_control
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L16_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L16_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L16_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L20_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L20_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L20_mixed
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L24_deceptive_only
Initial public release: SAE weights, cfg, and model card about 1 month ago
d32_topk_L24_honest_only
Initial public release: SAE weights, cfg, and model card about 1 month ago