INDEX

Explanations

references to significant individuals and scientific terminology

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

DeleteBehavior

-0.70

AndEndTag

-0.64

TabStop

-0.63

InjectAttribute

-0.63

webElementXpaths

-0.60

ResumeLayout

-0.60

Diwedd

-0.59

MessageTagHelper

-0.58

AndPassword

-0.57

ainte

-0.57

POSITIVE LOGITS

 مشين

0.47

pia

0.47

}();

0.47

',...

0.46

#+#

0.43

hematics

0.43

PRNewswire

0.42

ніципалі

0.41

 initComponents

0.41

 raccolta

0.41

Activations Density 0.008%

references to significant individuals and scientific terminology

No Comments

No Known Activations