INDEX

Explanations

the word "no" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 cref

-0.76

 ")");

-0.72

 متعلقه

-0.66

)*/

-0.65

 contribué

-0.65

 culturelles

-0.63

})*/

-0.62

 traite

-0.61

tersebut

-0.61

ynchronously

-0.59

POSITIVE LOGITS

no

2.36

No

2.07

No

2.00

NO

1.93

no

1.79

NO

1.62

Kein

1.39

 kein

1.31

Нет

1.27

 нет

1.25

Activations Density 0.212%

the word "no" in various contexts

No Comments

No Known Activations