INDEX

Explanations

terms related to open access publishing and licensing

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

ⓧ

-0.82

oredCriteria

-0.78

IonicModule

-0.72

 Administrativna

-0.70

rungsseite

-0.69

 بيها

-0.69

ariConfig

-0.69

unknownFields

-0.68

 bagay

-0.66

 ―――――

-0.66

POSITIVE LOGITS

 Attribution

1.06

Attribution

0.62

<eos>

0.57

 attribution

0.56

photobucket

0.53

Explicación

0.49

strides

0.47

creativecommons

0.44

TRIBUTION

0.44

UserScript

0.44

Activations Density 0.006%

terms related to open access publishing and licensing

No Comments

No Known Activations

terms related to open access publishing and licensing

No Comments

No Known Activations