INDEX

Explanations

references to archives and repository-related terms

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

 slutt

-0.64

+#+

-0.64

مقاله

-0.62

 ویکی‌پدیا

-0.61

JspWriter

-0.60

 idéia

-0.56

 Мексичка

-0.56

 batalha

-0.55

 fotografico

-0.55

معلومات

-0.55

POSITIVE LOGITS

archive

2.06

 archive

1.23

 Archive

1.17

Archive

1.13

ARCHIVE

1.13

存于互联网档案馆

0.93

 archives

0.83

ValueStyle

0.80

 consultato

0.77

archiv

0.77

Activations Density 0.028%

references to archives and repository-related terms

No Comments

No Known Activations