INDEX

Explanations

emotional terms and phrases indicating personal experiences or preferences

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

LookAnd

-0.73

AnchorStyles

-0.70

})));

-0.69

+#+#

-0.67

出版年

-0.64

']],

-0.57

OpenHelper

-0.57

 TestBed

-0.57

ForRow

-0.56

']?>

-0.54

POSITIVE LOGITS

 awesome

0.69

 glorious

0.64

awesome

0.63

0.62

good

0.62

 heure

0.61

 underrated

0.61

 good

0.58

 Awesome

0.58

tocin

0.58

Activations Density 0.171%

emotional terms and phrases indicating personal experiences or preferences

No Comments

No Known Activations