INDEX

Explanations

references to achievements or victories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 OFDb

-0.98

LookAnd

-0.89

 Мексичка

-0.80

 للمعارف

-0.78

WebElementEntity

-0.78

 PLWABN

-0.77

 Roskov

-0.77

 ویکی‌پدی

-0.75

]}

-0.75

tanleria

-0.74

POSITIVE LOGITS

win

0.88

Win

0.74

Win

0.74

won

0.74

win

0.73

WIN

0.69

 Winona

0.65

 Winn

0.63

Won

0.63

 wins

0.62

Activations Density 0.088%

references to achievements or victories

No Comments

No Known Activations