INDEX

Explanations

proper nouns and specific names associated with notable events 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

 uſed

-0.61

 fhort

-0.59

ſelf

-0.54

 auffi

-0.54

teenth

-0.51

 kolei

-0.50

خرى

-0.49

DMR

-0.49

Madeleine

-0.48

 forbin

-0.47

POSITIVE LOGITS

findpost

0.80

OGND

0.71

KommentareTeilen

0.66

InputBorder

0.63

ChildScrollView

0.63

зулта

0.63

httphttps

0.59

Autoritní

0.55

 يتيمه

0.54

Eksterne

0.54

Activations Density 0.508%

proper nouns and specific names associated with notable events or entities

No Comments

No Known Activations