INDEX

Explanations

references to propaganda and public relations campaigns

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

political campaigns and propaganda

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

ReusableCell

-0.44

 ujednoznacz

-0.43

AndEndTag

-0.40

Portail

-0.39

 podjela

-0.38

IVEREF

-0.37

ViewChild

-0.36

 cheese

-0.36

≦)

-0.36

Lähteet

-0.35

POSITIVE LOGITS

 campaign

2.33

 campaigns

2.19

campaign

2.02

 Campaign

1.98

 CAMPAIGN

1.95

Campaign

1.92

 campaña

1.90

 campagne

1.84

 Campaigns

1.82

 Kampagne

1.80

Activations Density 0.146%

references to propaganda and public relations campaigns

political campaigns and propaganda

No Comments

No Known Activations