INDEX

Explanations

mathematical expressions and probability-related notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ويكيميديا

-0.78

 DriverManager

-0.76

titleMargin

-0.73

AsUp

-0.71

 CommonModule

-0.66

webElementXpaths

-0.66

CrossRef

-0.66

glEnd

-0.62

varargin

-0.61

rceil

-0.60

POSITIVE LOGITS

MetaObject

0.71

íncia

0.70

boc

0.67

DrawerToggle

0.67

Predecesor

0.66

榄

0.63

 محفوظة

0.62

帖最后由

0.61

enumi

0.60

 lightest

0.59

Activations Density 0.363%

mathematical expressions and probability-related notation

No Comments

No Known Activations