INDEX

Explanations

code snippets related to the creation and manipulation of objects and classes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 transfieras

-0.72

ItemBackground

-0.66

HomeAsUpEnabled

-0.65

 समीक्षाओं

-0.61

ApiModel

-0.57

 AssemblyCulture

-0.55

 TextInputType

-0.55

SourceChecksum

-0.54

 unknownFields

-0.54

 betweenstory

-0.52

POSITIVE LOGITS

ⓧ

0.69

 getAge

0.69

 armées

0.67

objPHPExcel

0.66

 surla

0.64

 вікі

0.63

("}");

0.60

 pylint

0.59

levance

0.58

StateToProps

0.57

Activations Density 0.123%

code snippets related to the creation and manipulation of objects and classes

No Comments

No Known Activations