INDEX

Explanations

terminology associated with legal and governmental contexts

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

 Walkover

-0.42

CrossRef

-0.40

RenderAtEndOf

-0.39

 Nexus

-0.37

erweise

-0.35

سطس

-0.34

 Nada

-0.33

 дописавши

-0.33

EndGlobalSection

-0.33

 OFDb

-0.33

POSITIVE LOGITS

 مرئيه

0.50

 gång

0.47

 dormitorio

0.47

 bénéficiaire

0.47

couvrir

0.46

ámara

0.45

 plancher

0.45

Personensuche

0.44

transQ

0.43

 Administrativna

0.43

Activations Density 0.063%

terminology associated with legal and governmental contexts

No Comments

No Known Activations