INDEX

Explanations

references to specific TV shows and personalities

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

KommentareTeilen

-0.81

 NSCoder

-0.75

Datuak

-0.73

LookAnd

-0.71

 ftate

-0.69

 Diſ

-0.66

 дописавши

-0.66

 Reſ

-0.65

 Majefty

-0.63

 مشين

-0.63

POSITIVE LOGITS

</tr>

0.48

honneur

0.47

 host

0.46

on

0.45

Host

0.44

 station

0.44

Station

0.44

 hosts

0.44

station

0.43

рс

0.43

Activations Density 0.014%

references to specific TV shows and personalities

No Comments

No Known Activations