INDEX

Explanations

references to English and other languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Forumite

-0.81

 iſt

-0.79

存于互联网档案馆

-0.79

adays

-0.79

 itſelf

-0.79

 myſelf

-0.78

AutoScaleMode

-0.76

̈́

-0.74

 ſeveral

-0.74

.}~\

-0.74

POSITIVE LOGITS

 English

1.65

English

1.59

 english

1.22

english

1.19

 ENGLISH

1.17

ENGLISH

1.06

 inglés

0.91

英语

0.89

 Spanish

0.86

 Englisch

0.82

Activations Density 0.061%

references to English and other languages

No Comments

No Known Activations