INDEX

Explanations

references to political opposition and related entities

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

-0.72

 HasFactory

-0.71

machten

-0.70

wür

-0.68

 MediatR

-0.68

 liệu

-0.68

<?=

-0.67

 continuant

-0.64

 pulsera

-0.63

 Schülern

-0.63

POSITIVE LOGITS

 opposition

1.55

 Opposition

1.45

 oppos

1.41

Opposition

1.36

Opp

1.33

 oppose

1.30

opposition

1.29

 opposing

1.27

 opposes

1.27

Opp

1.24

Activations Density 0.073%

references to political opposition and related entities

No Comments

No Known Activations