INDEX

Explanations

terms related to animations and graphical programming

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-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/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.0.hook_mlp_out

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

HtmlAttribute

-0.68

antMatchers

-0.64

 mouseClicked

-0.60

consulté

-0.60

PageContext

-0.57

ReusableCell

-0.57

queryInterface

-0.54

 compac

-0.54

υμα

-0.54

 sauvage

-0.54

POSITIVE LOGITS

 Roskov

0.69

XmlType

0.62

NameInMap

0.56

 الحره

0.56

 beginnetje

0.53

 متعلقه

0.53

 &___

0.51

 redan

0.50

 mendes

0.49

Aholisi

0.49

Activations Density 0.263%

terms related to animations and graphical programming

No Comments

No Known Activations