INDEX

Explanations

references to a "view" in a programming or application development context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 BorderRadius

-0.87

 /\.(

-0.75

DispatchToProps

-0.71

fontawesome

-0.71

expandindo

-0.69

GeneratedMessage

-0.66

AlterField

-0.65

@"/

-0.65

Anhalt

-0.64

 kanssa

-0.63

POSITIVE LOGITS

 VIEW

1.29

 views

1.27

 VIEWS

1.22

 Views

1.20

 view

1.17

 View

1.16

views

1.14

VIEW

1.06

view

1.01

 viewDidLoad

0.98

Activations Density 0.065%

references to a "view" in a programming or application development context

No Comments

No Known Activations