INDEX

Explanations

references to privacy and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Carriera

-0.92

contentLoaded

-0.75

GEBURTSDATUM

-0.65

 NUKAT

-0.63

 protoimpl

-0.59

 Italijanski

-0.57

 Reverso

-0.57

WireFormat

-0.55

Fod

-0.55

 Савезне

-0.55

POSITIVE LOGITS

 White

0.72

White

0.68

RefreshLayout

0.65

}))

0.64

Inflater

0.63

 Initialized

0.61

 bianchi

0.60

white

0.60

WHITE

0.59

ruptedException

0.58

Activations Density 0.107%

references to privacy and related concepts

No Comments

No Known Activations