INDEX

Explanations

references to news-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Corbu

-0.43

itec

-0.38

occan

-0.38

batore

-0.38

appendChild

-0.37

 metade

-0.37

 ComVisible

-0.37

 Racine

-0.36

Volvo

-0.36

Korean

-0.36

POSITIVE LOGITS

 news

2.05

 News

1.92

News

1.79

 NEWS

1.78

news

1.77

NEWS

1.59

 noticia

1.36

 berita

1.30

 noticias

1.30

 notícia

1.25

Activations Density 0.126%

references to news-related content

No Comments

No Known Activations