INDEX

Explanations

technical terms and metrics related to performance and efficiency in systems or processes

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 AssemblyVersion

-0.53

bootstrapcdn

-0.51

 subida

-0.51

 huelga

-0.48

 perfección

-0.47

 vectorielle

-0.47

Identyfik

-0.47

 saveiro

-0.47

 spéciaux

-0.46

 vectorielles

-0.46

POSITIVE LOGITS

UseVisualStyle

0.41

Browsable

0.39

internalType

0.37

越

0.36

utal

0.36

})).

0.35

 eter

0.35

 amen

0.35

;->

0.35

 popo

0.35

Activations Density 0.129%

technical terms and metrics related to performance and efficiency in systems or processes

No Comments

No Known Activations