INDEX

Explanations

phrases indicating levels of measurement or intensity in various contexts

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

 Favorites

-0.62

 pescoço

-0.60

 favorites

-0.59

 kraft

-0.59

XmlType

-0.59

 peup

-0.58

 termica

-0.57

LogFactory

-0.56

tableFuture

-0.55

 linkovi

-0.54

POSITIVE LOGITS

脚注の使い方

1.06

 levels

0.94

 level

0.93

 amount

0.91

 poziom

0.87

Levels

0.85

levels

0.78

providedIn

0.77

 tingkat

0.77

 Levels

0.75

Activations Density 0.256%

phrases indicating levels of measurement or intensity in various contexts

No Comments

No Known Activations