INDEX

Explanations

mathematical symbols and notation used in statistical models and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 mathvariant

-0.66

YNC

-0.62

ABU

-0.57

maphore

-0.56

clairage

-0.55



-0.53

rawDesc

-0.53

ανά

-0.52

hofen

-0.51

 normalize

-0.51

POSITIVE LOGITS

Portail

0.90

MethodManager

0.87

 endregion

0.70

 betweenstory

0.69

 الحره

0.69

localctx

0.64

MigrationBuilder

0.63

InjectAttribute

0.62

ImageContext

0.61

IndentedString

0.61

Activations Density 0.502%

mathematical symbols and notation used in statistical models and processes

No Comments

No Known Activations