INDEX

Explanations

references to emotional states and emotional impacts

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

IntentFilter

-0.69

()]

-0.68

 referenties

-0.68

kegaard

-0.67

Tembelea

-0.67

出版年

-0.66

 NavController

-0.66

κει

-0.65

ⓧ

-0.65

ябре

-0.63

POSITIVE LOGITS

chluss

0.68

 Fantas

0.66

шно

0.63

 Ehre

0.63

 reaſon

0.62

cão

0.60

 emotionally

0.59

 Gerr

0.59

 reassurance

0.59

Emotional

0.59

Activations Density 0.003%

references to emotional states and emotional impacts

No Comments

No Known Activations

references to emotional states and emotional impacts

No Comments

No Known Activations