INDEX

Explanations

phrases related to conversion and transformation processes in programming and data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

mybatisplus

-0.67

UnknownFields

-0.62

 ***!

-0.62

AnimationsModule

-0.56

DotNetBar

-0.55

TintMode

-0.53

 InputDecoration

-0.53

UnitTesting

-0.53

Население

-0.52

fromnode

-0.51

POSITIVE LOGITS

 usable

0.90

 manageable

0.85

 readable

0.75

 workable

0.73

 accessible

0.72

 understandable

0.70

Personensuche

0.70

 searchable

0.70

 digestible

0.69

 consuma

0.67

Activations Density 0.483%

phrases related to conversion and transformation processes in programming and data manipulation

No Comments

No Known Activations