INDEX

Explanations

terms and phrases related to legislative and informational contexts

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

-0.46

strij

-0.43

hamos

-0.42

 real

-0.42

ha

-0.41

car

-0.39

 process

-0.39

and

-0.39

-0.38

iche

-0.38

POSITIVE LOGITS



0.89

Personensuche

0.88

IntoConstraints

0.80

 تضيفلها

0.79

SourceChecksum

0.78

########.

0.78

octanol

0.76

ImageContext

0.76

 nakalista

0.75

ChildScrollView

0.75

Activations Density 0.421%

terms and phrases related to legislative and informational contexts

No Comments

No Known Activations

terms and phrases related to legislative and informational contexts

No Comments

No Known Activations