INDEX

Explanations

elements related to emotional engagement and interest in activities or narratives

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.60

HtmlAttribute

-0.55

EDEFAULT

-0.54

 ComVisible

-0.53

 MaterialApp

-0.53

fxml

-0.52

SLASH

-0.52

 Accident

-0.50

ClientRect

-0.50

abetes

-0.48

POSITIVE LOGITS

 excite

0.59

RegistryLite

0.59

 интере

0.58

 interessanti

0.57

DockStyle

0.56

 interesting

0.56

 Spannung

0.56

Filler

0.56

HasAnnotation

0.56

 novelty

0.55

Activations Density 0.128%

elements related to emotional engagement and interest in activities or narratives

No Comments

No Known Activations