GitHub topics: steering-vector
codelion/pts
Pivotal Token Search
Language: Python - Size: 200 KB - Last synced at: 28 days ago - Pushed at: 28 days ago - Stars: 6 - Forks: 1
seonglae/emgsd-hermes
Steering GPT2-EMGSD less biased & Generating stereotyped text with vanilla GPT2 without fine tuning or prompt engineering
Language: Jupyter Notebook - Size: 505 KB - Last synced at: 26 days ago - Pushed at: 3 months ago - Stars: 2 - Forks: 0
Related Keywords
steering-vector
2
sparse-autoencoder
2
stereotype
1
gpt2
1
emgsd
1
bias-mitigation
1
bias-correction
1
tokens
1
sae
1
reasoning-models
1
reasoning-language-models
1
reasoning-agent
1
pivotal-tokens
1
pivotal-token-search
1
phi4-mini
1
phi4
1
phi-4-mini
1
phi-4
1
mech-interp
1
llm-steering
1
llm-inference
1
llm
1
dpo
1
direct-preference-optimization
1
dataset-generation
1