agu18dec
/

olens-ablations

interpretability

activation-reading

Model card Files Files and versions

olens-ablations / gradient_target

2.91 GB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

agu18dec's picture

Add RL variants (co-trained AR, advantage normalisation), bullet readouts, gradient target, bare-model log reward

a1987eb verified 4 days ago

ar
Add RL variants (co-trained AR, advantage normalisation), bullet readouts, gradient target, bare-model log reward 4 days ago
inverter
Add RL variants (co-trained AR, advantage normalisation), bullet readouts, gradient target, bare-model log reward 4 days ago
inverter_rl_on_activations
Add RL variants (co-trained AR, advantage normalisation), bullet readouts, gradient target, bare-model log reward 4 days ago
lens_rl_step150
Add RL variants (co-trained AR, advantage normalisation), bullet readouts, gradient target, bare-model log reward 4 days ago
lens_rl_step300
Add RL variants (co-trained AR, advantage normalisation), bullet readouts, gradient target, bare-model log reward 4 days ago