INDEX

Explanations

mathematical expressions and notation used in scientific contexts

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

 auprès

-0.52

elerik

-0.51

gorithm

-0.50

loyees

-0.49

 appartiennent

-0.49

 déclar

-0.49

 mắn

-0.48

 zoude

-0.48

mặt

-0.48

hidupan

-0.48

POSITIVE LOGITS

脚注の使い方

0.90

IsMutable

0.79

UnusedPrivate

0.74

########.

0.71

XmlEnum

0.68

tagHelperRunner

0.68

}.

0.67

 Theſe

0.66

})).

0.66

oredCriteria

0.64

Activations Density 2.216%

mathematical expressions and notation used in scientific contexts

No Comments

No Known Activations