INDEX

Explanations

references to imported items or goods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

تقاوى

-0.56

 /\.(

-0.55

 labor

-0.52

numerusform

-0.51

SPATH

-0.51

addContainerGap

-0.50

 jauh

-0.50

 indexPath

-0.49

Abp

-0.48

 חוש

-0.47

POSITIVE LOGITS

 imported

0.89

imported

0.80

 Imported

0.78

 immig

0.74

ATT

0.74

 immigration

0.73

Immigration

0.68

 importation

0.68

 Immigration

0.67

 imports

0.66

Activations Density 0.159%

references to imported items or goods

No Comments

No Known Activations