INDEX

Explanations

programming-related identifiers and keywords, specifically focusing on variable names and parameters within code constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ContentLoaded

-0.51

bootstrapcdn

-0.51

Obrázky

-0.43

UnusedPrivate

-0.43

nonatomic

-0.43

IsContent

-0.42

agisse

-0.41

انيا

-0.41

بوابة

-0.40

AnchorStyles

-0.39

POSITIVE LOGITS

bibfield

0.76

bibinfo

0.72

曖昧さ回避

0.72

 theſe

0.69

tvguidetime

0.68

FOOTNOTES

0.67

 myſelf

0.67

 nahilalakip

0.65

 ſuch

0.64

vius

0.64

Activations Density 0.325%

programming-related identifiers and keywords, specifically focusing on variable names and parameters within code constructs

No Comments

No Known Activations