INDEX

Explanations

technical terms and identifiers related to programming and APIs

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



-0.59

ViewImports

-0.51

 zufolge

-0.48

 استنادى

-0.47

WillAppear

-0.47

Bromoform

-0.43

getSeconds

-0.42

 Aussch

-0.42

 besk

-0.41

 σχέ

-0.41

POSITIVE LOGITS

GEBURTSDATUM

0.54

Autoritní

0.54

 فريبيس

0.48

 Type

0.47

propTypes

0.47

WebVitals

0.47

 type

0.45

 TextInputType

0.45

 חיצוניים

0.43

Chin

0.43

Activations Density 0.001%

technical terms and identifiers related to programming and APIs

No Comments

No Known Activations