INDEX

Explanations

prepositions indicating relationships or positions

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

Negative Logits

 himſelf

-0.76

 themſelves

-0.75

ſelf

-0.72

 chofe

-0.72

 leaſt

-0.71

 myſelf

-0.71

 Reſ

-0.70

 poffe

-0.69

 becauſe

-0.68

Eſ

-0.68

POSITIVE LOGITS

 '\\;'

0.69

libft

0.68

Obrázky

0.63

 getBy

0.62

;">

0.61

 Pristupljeno

0.60

Ecotoxicity

0.59

Hentet

0.59

peutic

0.58

ngilizce

0.57

Activations Density 0.068%

prepositions indicating relationships or positions

No Known Activations