INDEX

Explanations

expressions related to violence or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.75

enumi

-0.66

 CreateTagHelper

-0.63

"}")

-0.63

 للاسماء

-0.63

########.

-0.62

}');

-0.59

 Wikimedijinoj

-0.58

ArrowToggle

-0.57

 intptr

-0.57

POSITIVE LOGITS

muka

0.56

 your

0.55

you

0.53

Let

0.53

 Brother

0.53

IConfiguration

0.53

our

0.52

your

0.50

 brother

0.49

 miei

0.48

Activations Density 0.040%

expressions related to violence or conflict

No Comments

No Known Activations