INDEX

Explanations

indices related to specific scientific or technical subjects

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

 تضيفلها

-0.71

LEncoder

-0.69

etcode

-0.63

hoeddwyd

-0.62

 tslint

-0.57

ngdoc

-0.56

 '\\;'

-0.55

UrlResolution

-0.55

MessageTagHelper

-0.54

 GenerationType

-0.51

POSITIVE LOGITS

VERTIS

0.52

 Stephenson

0.51

alline

0.50

eh

0.50

 they

0.49

hemd

0.49

}();

0.49

openSession

0.49

Ob

0.48

ameter

0.48

Activations Density 1.970%

indices related to specific scientific or technical subjects

No Known Activations