INDEX

Explanations

references or citations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

hasMoreElements

-0.87

 సౌకర్య

-0.76

 AttributeSet

-0.71

Abitanti

-0.70

Enlaces

-0.70

archiviato

-0.68

Климат

-0.66

 endwhile

-0.66

CppCodeGen

-0.65

 Italijani

-0.65

POSITIVE LOGITS

↑

0.83

 https

0.80

 http

0.76

https

0.62

«

0.60

})));

0.60

())));

0.56

http

0.55

}}">

0.54

0.51

Activations Density 0.050%

references or citations in the text

No Comments

No Known Activations