INDEX

Explanations

instances of the word "props" in a coding context

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

]]

-0.83

SourceChecksum

-0.82

 Drapeau

-0.80

ьаж

-0.80

UnusedPrivate

-0.79

 /\.(

-0.74

ignty

-0.72

Portail

-0.72

hasMoreElements

-0.71

protoimpl

-0.70

POSITIVE LOGITS

props

2.53

 props

1.85

Props

1.73

 Props

1.48

PROPS

1.20

nextProps

0.87

Properties

0.79

 prop

0.75

 Properties

0.72

 properties

0.64

Activations Density 0.017%

instances of the word "props" in a coding context

No Comments

No Known Activations