INDEX

Explanations

technical terminology related to statistical modeling and analysis

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

 intptr

-0.64

WireFormatLite

-0.60

ոլ

-0.59

GeoNames

-0.56

vosť

-0.54

իլ

-0.53

mathrm

-0.52

աշ

-0.51

UnknownFieldSet

-0.51

IContainer

-0.50

POSITIVE LOGITS

ContentAsync

0.86

ChildScrollView

0.83

<bos>

0.73

 EdgeInsets

0.73

 تضيفلها

0.72

WebVitals

0.69

tagHelperRunner

0.67

 CURIAM

0.65

 مشين

0.65

 onlyOwner

0.65

Activations Density 18.256%

technical terminology related to statistical modeling and analysis

No Comments

No Known Activations