INDEX

Explanations

references to figures, tables, and detailed descriptions in scientific documents

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

 الرياضيه

-0.76

GEBURTSDATUM

-0.66

ंदीखरीदारी

-0.65

WebServlet

-0.65

 autorytatywna

-0.65

QMetaType

-0.63

Autoritní

-0.61

Jeografia

-0.58

urlpatterns

-0.58

Identyfik

-0.58

POSITIVE LOGITS

 details

0.67

 فہرست

0.62

 summarized

0.61

詳しい

0.60

 illustrated

0.59

 summarised

0.58

詳細は

0.58

details

0.57

 detailed

0.57

详

0.57

Activations Density 1.761%

references to figures, tables, and detailed descriptions in scientific documents

No Comments

No Known Activations