INDEX

Explanations

accounts of violent acts and justifications for violence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

noons

-0.64

 laude

-0.63

anek

-0.62

featureID

-0.59

errHandler

-0.57

/>\

-0.56

ReusableCell

-0.55

enment

-0.55

icolon

-0.55

 Perfection

-0.55

POSITIVE LOGITS

 violence

0.78

 injuring

0.75

 violent

0.73

 wounding

0.64

 homicide

0.64

 EconPapers

0.63

 injured

0.63

 Violent

0.63

 murder

0.62

violence

0.62

Activations Density 0.532%

accounts of violent acts and justifications for violence

No Comments

No Known Activations