INDEX

Explanations

numerical values and codes present in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

endphp

-0.76

fikasi

-0.70

angeran

-0.67

MediaStore

-0.66

 Processed

-0.66

 Buren

-0.66

 Proceed

-0.61

hyung

-0.60

UrlEncoded

-0.58

processed

-0.58

POSITIVE LOGITS

OGND

0.78

AndEndTag

0.76

gggg

0.70

ating

0.70

izing

0.65

ting

0.58

GGGG

0.57

bing

0.57

Taking

0.57

vating

0.57

Activations Density 0.981%

numerical values and codes present in data

No Comments

No Known Activations