INDEX

Explanations

conjunctions and phrases indicating connections between concepts or entities

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

 noqa

-0.85

windowFixed

-0.81

 rhestr

-0.80

DockStyle

-0.79

 onAnimation

-0.76

tonode

-0.75

 للمعارف

-0.68

AndEndTag

-0.68

 Corbu

-0.68

 Савезне

-0.66

POSITIVE LOGITS

bootstrapcdn

0.58

Description

0.50

 humaines

0.50

 verdi

0.45

standig

0.45

 चुनें

0.43

]])

0.42

yw

0.41

</code>

0.40

Strategy

0.40

Activations Density 0.023%

conjunctions and phrases indicating connections between concepts or entities

No Comments

No Known Activations