INDEX

Explanations

instances of the word "won."

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

 propOrder

-0.96

 ModelExpression

-0.91

 ویکی‌پدیای

-0.83

TemporalType

-0.83

AsUp

-0.82

 ffilmiau

-0.76

ValueStyle

-0.72

RenderAtEndOf

-0.71

 disambiguazione

-0.69

 فريبيس

-0.69

POSITIVE LOGITS

won

1.93

won

1.74

Won

1.64

Won

1.63

WON

1.50

WON

1.24

 wont

1.21

 ganó

0.65

Will

0.60

 vinto

0.60

Activations Density 0.046%

instances of the word "won."

No Comments

No Known Activations