INDEX

Explanations

references to the concept of "nature."

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

NATURAL

-0.70

natural

-0.68

Natural

-0.67

 NATURAL

-0.63

 natürliche

-0.63

 Natural

-0.62

 scallops

-0.61

WaitGroup

-0.61

 profi

-0.60

ambiental

-0.60

POSITIVE LOGITS

 NATURE

0.91

 nature

0.89

 Nature

0.84

NATURE

0.83

 natureza

0.80

Nature

0.75

 виправивши

0.75

ècie

0.74

Vader

0.72

nature

0.69

Activations Density 0.006%

references to the concept of "nature."

No Comments

No Known Activations

references to the concept of "nature."

No Comments

No Known Activations