INDEX

Explanations

mentions of deceitful or fraudulent activities and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ollectionView

-0.82

 participaron

-0.77

berdayakan

-0.77

tamment

-0.69

ModelAdmin

-0.68

 trouvera

-0.66

amaño

-0.66

 debout

-0.65

 familiale

-0.64

 parlant

-0.64

POSITIVE LOGITS

 fake

1.79

 Fake

1.56

fake

1.50

Fake

1.50

 faking

1.30

 false

1.29

 fakes

1.28

 pretend

1.27

 phony

1.24

 faked

1.24

Activations Density 0.328%

mentions of deceitful or fraudulent activities and concepts

No Comments

No Known Activations