INDEX

Explanations

technical terms related to machine learning and data science

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

ThroughAttribute

-0.69

 noDo

-0.61

 resourceCulture

-0.59

 AssemblyCompany

-0.56

лтемелер

-0.55

 AssemblyCulture

-0.53

 recruited

-0.53

ModelAdmin

-0.53

OLEAN

-0.52

Välislingid

-0.52

POSITIVE LOGITS

 antiquated

0.42

 vintage

0.41

Personensuche

0.40

Telegram

0.40

DeleteBehavior

0.39

 nonatomic

0.38

nameof

0.38

 historical

0.37

 viejo

0.36

messageInfo

0.36

Activations Density 0.219%

technical terms related to machine learning and data science

No Comments

No Known Activations