INDEX

Explanations

references to computer programming or coding-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 handleMessage

-0.54

ApiOperation

-0.52

 ویکی‌آمباردا

-0.49

例句

-0.46

can

-0.46

invokeLater

-0.45

 här

-0.43

erdere

-0.42

Ӕ

-0.42

 mouseY

-0.41

POSITIVE LOGITS

 "..\..\..\

0.97

IntoConstraints

0.97

 "..\..\

0.92

 ویکی‌پدی

0.80

owol

0.71

oldown

0.71

SourceChecksum

0.67

arynx

0.67

abestanden

0.65

 تعدى

0.65

Activations Density 0.042%

references to computer programming or coding-related terms

No Comments

No Known Activations