INDEX

Explanations

instances of participation in activities or events

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

endregion

-0.45

 lhes

-0.44

LookAnd

-0.43

 Berlín

-0.42

 pihaknya

-0.41

SourceChecksum

-0.41

лтемелер

-0.41

uens

-0.40

 memand

-0.40

 kepad

-0.38

POSITIVE LOGITS

 participate

0.87

particip

0.77

Particip

0.75

 participated

0.73

 participating

0.73

 Particip

0.73

 participatory

0.69

 Participate

0.68

 participates

0.68

 participant

0.68

Activations Density 0.028%

instances of participation in activities or events

No Comments

No Known Activations