INDEX

Explanations

mentions of "Americans."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

بوابة

-0.54

 Mahoney

-0.49

NY

-0.49

poque

-0.48

let

-0.46

ilant

-0.44

sua

-0.44

 ре

-0.44

出会い

-0.44

nyt

-0.43

POSITIVE LOGITS

 Americans

2.56

 Germans

2.44

 Australians

2.40

 Canadians

2.36

 Russians

2.35

Americans

2.32

 Italians

2.30

 Nigerians

2.29

 Indians

2.27

 Spaniards

2.20

Activations Density 0.106%

mentions of "Americans."

No Comments

No Known Activations