INDEX

Explanations

specific formatting or labeling within structured 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

曖昧さ回避

-0.47

 accomp

-0.41

 dazu

-0.41

POINTER

-0.40

 adicionales

-0.40

his

-0.40

 that

-0.40

 trở

-0.40

 通販

-0.39

arsch

-0.39

POSITIVE LOGITS

IsContent

0.92

__':

0.87

 Jefus

0.83

__':

0.78

TagMode

0.74

"]="

0.72

OGND

0.71

ConstraintMaker

0.71

 चीज़ों

0.70

Hentet

0.68

Activations Density 0.316%

specific formatting or labeling within structured data

No Comments

No Known Activations