INDEX

Explanations

programming-related keywords and elements associated with user interface development

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

code or programming

np_acts-logits-general · gemini-2.0-flash

programming identifiers and keywords

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

HtmlAttribute

-0.59

tagext

-0.58

//});

-0.58

stateProvider

-0.58

spesies

-0.57

 uſed

-0.57

 TableColumn

-0.54

 koke

-0.54

 jsPsych

-0.53

avits

-0.52

POSITIVE LOGITS

RenderAtEndOf

0.76

SourceChecksum

0.63

Diwedd

0.54

 final

0.54

DispatchToProps

0.54

tanleria

0.54

FOOTNOTES

0.53

public

0.51

 externi

0.49

 autorytatywna

0.49

Activations Density 0.037%

programming-related keywords and elements associated with user interface development

code or programming

programming identifiers and keywords

No Comments

No Known Activations