INDEX

Explanations

phrases indicating uncertainty or ambiguity in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 ogóle

-0.63

 pageContext

-0.54

Spoljašnje

-0.50

Jeografia

-0.48

}*/

-0.47

 Orrell

-0.47

apimachinery

-0.47

idane

-0.46

 membuatnya

-0.45

MessageOf

-0.45

POSITIVE LOGITS

+#+#

0.72

HtmlAttribute

0.72

 <<<<<<<<<<<<<<

0.68

 Савезне

0.66

ValueStyle

0.66

 تضيفلها

0.66

rxjs

0.57

EndInit

0.57

awtextra

0.57

cabo

0.55

Activations Density 0.869%

phrases indicating uncertainty or ambiguity in statements

No Comments

No Known Activations