INDEX

Explanations

elements related to data encoding, especially character sets and formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 مرئيه

-0.76

AccessorTable

-0.76

 ivelany

-0.73

GOTREF

-0.70

WaitGroup

-0.67

ReusableCell

-0.66

 élevées

-0.65

 complètes

-0.64

complexContent

-0.63

 TestBed

-0.63

POSITIVE LOGITS

 charset

0.57

JIS

0.55

Unicode

0.53

 Unicode

0.52

charset

0.50

utf

0.47

encoding

0.47

 Emoji

0.46

 emojis

0.46

LEncoder

0.45

Activations Density 1.000%

elements related to data encoding, especially character sets and formats

No Comments

No Known Activations