INDEX

Explanations

key identifiers or markers related to topics or geographic locations

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

 kasarigan

-0.85

AntiForgeryToken

-0.79

 للمعارف

-0.73

 Chwiliwch

-0.69

GEBURTSDATUM

-0.65

kháu

-0.65

 propOrder

-0.64

WebElementEntity

-0.63

delwed

-0.62

存于互联网档案馆

-0.59

POSITIVE LOGITS

 dönüş

0.40

 compartió

0.36

 tapasztal

0.36

 compartir

0.36

strij

0.34

Satisfied

0.34

 Pohl

0.34

 encontró

0.33

SessionManager

0.33

 welcome

0.33

Activations Density 0.002%

key identifiers or markers related to topics or geographic locations

No Comments

No Known Activations