INDEX

Explanations

elements or structures in programming or markup languages

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

hyrchwyd

-0.66

photobucket

-0.65

 estekak

-0.64

 nahilalakip

-0.56

 saites

-0.56

 astfel

-0.53

winder

-0.52

MessageInfo

-0.52

__(/*!

-0.51

XmlAccessorType

-0.51

POSITIVE LOGITS

 DataTypes

0.54

AsUp

0.54

territory

0.53

aspectj

0.53

 Drapeau

0.51

">—

0.51

 AttributeSet

0.49

statue

0.48

வர்

0.48

 Agreement

0.48

Activations Density 1.042%

elements or structures in programming or markup languages

No Comments

No Known Activations