INDEX

Explanations

references to different nationalities and ethnic groups

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.69

baa

-0.53

ciel

-0.51

въ

-0.50

stet

-0.50

 atra

-0.50

Adi

-0.48

crop

-0.48

Aziz

-0.47

벌

-0.47

POSITIVE LOGITS

 Canadians

1.25

 Americans

1.24

Americans

1.20

 Nigerians

1.13

 Australians

1.09

 Britons

1.07

 Israelis

1.06

 Kenyans

1.04

 Ghanaians

1.04

 Koreans

1.03

Activations Density 0.278%

references to different nationalities and ethnic groups

No Comments

No Known Activations