INDEX

Explanations

terms associated with justification and self-defense in conflict scenarios

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

Threat, danger, or potential harm

np_acts-logits-general · gemini-2.0-flash

threat and danger

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 <>",

-0.74

 ModelExpression

-0.65

]--;

-0.65

igraphic

-0.61

 Thebes

-0.60

CommonModule

-0.60

צלחה

-0.58

ativität

-0.57

ulite

-0.55

 WebDriverWait

-0.54

POSITIVE LOGITS

 threat

0.81

 threatening

0.77

 harmless

0.76

Geplaatst

0.73

Threat

0.70

 disarm

0.69

 Threat

0.69

 menacing

0.69

 danger

0.69

 threats

0.69

Activations Density 0.292%

terms associated with justification and self-defense in conflict scenarios

Threat, danger, or potential harm

threat and danger

No Comments

No Known Activations