INDEX

Explanations

references to enclosures or containing structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

enclosed or enclosure

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

truly

-0.48

iri

-0.48

thyst

-0.42

Truly

-0.42

archiviato

-0.42

Darth

-0.42

ApiProperty

-0.42

setopt

-0.41

ibase

-0.41

sendKeys

-0.40

POSITIVE LOGITS

 praça

0.56

aperto

0.52

LookAnd

0.52

 plegable

0.48

 चीज़ों

0.48

 jaula

0.48

 cappello

0.46

 cervello

0.45

 ProtoMessage

0.45

IntoConstraints

0.45

Activations Density 0.012%

references to enclosures or containing structures

enclosed or enclosure

No Comments

No Known Activations