INDEX

Explanations

instances of the keyword "new" in code, indicating object creation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 propOrder

-0.76

 IService

-0.75

 Mahomet

-0.75

Хьажоргаш

-0.74

хьтан

-0.72

oredCriteria

-0.71

 postIndex

-0.70

 disambiguazione

-0.70

 فريبيس

-0.69

 itſelf

-0.68

POSITIVE LOGITS

new

0.88

new

0.85

newFile

0.76

New

0.65

newArrayList

0.62

amerikanischer

0.62

 struct

0.62

 typename

0.61

 White

0.61

 $("<

0.61

Activations Density 0.047%

instances of the keyword "new" in code, indicating object creation

No Comments

No Known Activations