INDEX

Explanations

references to scientific or technical measurement details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

featureID

-0.81

Personensuche

-0.77

 resourceCulture

-0.74

AnchorStyles

-0.73

MethodManager

-0.70

setVerticalGroup

-0.70

 تضيفلها

-0.69

BagConstraints

-0.68

 հղումներ

-0.67

CloseOperation

-0.67

POSITIVE LOGITS

 serisi

0.60

 series

0.53

 série

0.52

liceerd

0.50

series

0.50

 Family

0.46

 Lyra

0.46

 Series

0.45

 family

0.44

Activations Density 0.292%

references to scientific or technical measurement details

No Comments

No Known Activations