INDEX

Explanations

contextual references to locations and events

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.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

 sustitu

-0.32

 itemprop

-0.29

rouvez

-0.29

 categories

-0.29

stoff

-0.28

 border

-0.28

теристики

-0.28

Bab

-0.28

回头

-0.28

Juli

-0.28

POSITIVE LOGITS

 OFDb

0.75

 betweenstory

0.63

رشف

0.63

 invokingState

0.57

InputBorder

0.56

 ProtoMessage

0.56

RTEE

0.56

ंदीखरीदारी

0.56

AnchorStyles

0.55

DeleteBehavior

0.55

Activations Density 0.010%

contextual references to locations and events

No Comments

No Known Activations