INDEX

Explanations

terms and phrases related to news broadcasting networks

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.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

évaluateur

-0.62

zzleHttp

-0.60

 autorytatywna

-0.59

Autoritní

-0.58

jamientos

-0.54

yntaxException

-0.51

 estekak

-0.49

 CanadaChoose

-0.47

+#+#

-0.47

 ComVisible

-0.47

POSITIVE LOGITS

 news

1.52

news

1.14

 News

1.10

 noticias

1.01

News

1.01

 berita

0.97

 NEWS

0.95

新闻

0.93

ニュース

0.92

 뉴스

0.92

Activations Density 0.162%

terms and phrases related to news broadcasting networks

No Comments

No Known Activations