INDEX

Explanations

references to political power dynamics and threats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.70

 gemeenten

-0.63

ImageContext

-0.62

олові

-0.61

 addSubview

-0.60

ObjectContext

-0.57

objc

-0.56

featureID

-0.56

 propOrder

-0.56

庁

-0.55

POSITIVE LOGITS

 invasion

0.89

war

0.84

 aggressor

0.81

 aggression

0.79

 invaded

0.79

 invading

0.76

 invade

0.75

 invasions

0.72

invasion

0.72

 bombing

0.71

Activations Density 0.579%

references to political power dynamics and threats

No Comments

No Known Activations