INDEX

Explanations

commands related to retrieving and processing arguments within a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__":

-0.68

__':

-0.68

KURZBESCHREIBUNG

-0.65

__':

-0.64

contentLoaded

-0.59

__":

-0.58

Datuak

-0.58

 дописавши

-0.56

 Chwiliwch

-0.54

 ligiloj

-0.52

POSITIVE LOGITS

 propOrder

0.67

 objectForKey

0.60

jsxFileName

0.60

 bool

0.55

 Bool

0.54

 getString

0.53

bool

0.53

 getInt

0.51

containsKey

0.51

 AttributeSet

0.50

Activations Density 0.206%

commands related to retrieving and processing arguments within a programming context

No Comments

No Known Activations