INDEX

Explanations

descriptions of physical positions or stances of objects or individuals

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

parsedMessage

-0.73

RegressionTest

-0.60

 Extragalactic

-0.56

 Meksiku

-0.56

żdy

-0.55

 dAtA

-0.55

fillType

-0.54

InjectAttribute

-0.54

errHandler

-0.53

@[+][

-0.52

POSITIVE LOGITS

 propOrder

0.73

 مُعرِّف

0.64

jsonwebtoken

0.63

brainly

0.63

antMatchers

0.60

 midline

0.59

<!--[

0.59

 useRouter

0.58

BeanUtils

0.56

amental

0.56

Activations Density 0.007%

descriptions of physical positions or stances of objects or individuals

No Comments

No Known Activations