INDEX

Explanations

references to people, locations, and organizations, especially in relation to the United States

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

"American," "USA" or the United States

np_acts-logits-general · gemini-2.0-flash

American and USA references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

colgante

-0.46

cartão

-0.45

 Cement

-0.41

 arrêt

-0.41

 pretense

-0.40

Legături

-0.40

 taşı

-0.39

 CURLOPT

-0.39

 debout

-0.39

 étudiants

-0.39

POSITIVE LOGITS

USA

1.05

在美国

1.04

 American

1.02

 America

1.02

🇺🇸

0.98

US

0.98

USA

0.94

 американ

0.94

アメリカ

0.93

American

0.92

Activations Density 0.876%

references to people, locations, and organizations, especially in relation to the United States

"American," "USA" or the United States

American and USA references

No Comments

No Known Activations