INDEX

Explanations

numeric values and data structure properties

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 tartalomajánló

-0.67

Chham

-0.61

ItemBackground

-0.60

 unknownFields

-0.56

XmlAccessorType

-0.54

 voie

-0.54

-0.53

 Chwiliwch

-0.53

arynge

-0.52

 Référence

-0.52

POSITIVE LOGITS

mapStateToProps

0.61

EndInit

0.56

tangentMode

0.56

 NSCoder

0.53

 conditions

0.53

 level

0.51

CodeAttribute

0.50

formik

0.50

Sklici

0.50

Activations Density 0.010%

numeric values and data structure properties

No Comments

No Known Activations