INDEX

Explanations

instances of the word "for" used in various contexts and phrases

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

XmlAccessType

-0.93

ImageContext

-0.89

 للمعارف

-0.80

 CreateTagHelper

-0.80

 <>",

-0.79

principalColumn

-0.78

XmlRootElement

-0.78

Geplaatst

-0.76

 OnInit

-0.75

IsPostBack

-0.75

POSITIVE LOGITS

 many

0.69

 those

0.67

 years

0.66

 most

0.66

 some

0.65

 whatever

0.63

unately

0.60

cing

0.59

me

0.58

For

0.57

Activations Density 0.119%

instances of the word "for" used in various contexts and phrases

No Comments

No Known Activations