INDEX

Explanations

keywords and actions associated with setting and updating system properties or conditions

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

WireFormat

-0.63

Fio

-0.52

 lately

-0.49

 Administrativna

-0.49

Loja

-0.48

toPromise

-0.47

ISTS

-0.47

Geograf

-0.47

divided

-0.47

 divided

-0.46

POSITIVE LOGITS

Hentet

0.63

 ویکی‌پدی

0.59

aarrggbb

0.59

AddTagHelper

0.57

AlterField

0.56

mappedBy

0.55

 SafeMath

0.55

enumi

0.54

InjectAttribute

0.53

 beginnetje

0.53

Activations Density 0.187%

keywords and actions associated with setting and updating system properties or conditions

No Comments

No Known Activations