Text Generation
Transformers
emotion-vectors
interpretability
mechanistic-interpretability
replication
gemma4
google
anthropic
valence-arousal
PCA
logit-lens
linear-probe
probing
emotion
functional-emotions
AI-safety
neuroscience
circumplex-model
activation-extraction
residual-stream
Eval Results (legacy)
| torch>=2.0.0 | |
| transformers>=5.0.0 | |
| numpy>=1.24.0 | |
| matplotlib>=3.7.0 | |