INDEX

Explanations

phrases related to political oppression and resistance efforts

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

出版年

-0.63

 SafeMath

-0.52

DeleteMapping

-0.51

})]

-0.46

PathParam

-0.45

 sufferer

-0.45

 disponibilités

-0.45

Queryable

-0.45

 Lightboxes

-0.45

OGND

-0.45

POSITIVE LOGITS

 sabotage

0.73

 fieldNum

0.67

 malicious

0.65

 Plot

0.65

 opposition

0.65

 Organized

0.65

 plot

0.64

 enemy

0.63

bilisi

0.62

 organized

0.61

Activations Density 0.364%

phrases related to political oppression and resistance efforts

No Comments

No Known Activations