INDEX

Explanations

terms related to professional health and research methodologies

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

.*")]

-0.68

 Jahrhunderts

-0.60

ferrer

-0.57

UserScript

-0.56

 ostavi

-0.56

 oprot

-0.53

Jährige

-0.50

 doInBackground

-0.50

SharedDtor

-0.49

POSITIVE LOGITS

LookAnd

0.68

 ModelExpression

0.58

 ITIS

0.57

Vidite

0.56

YourGuide

0.54

ustris

0.53

 Мексичка

0.53

édia

0.52

UnknownFieldSet

0.52

 CreateTagHelper

0.48

Activations Density 0.298%

terms related to professional health and research methodologies

No Known Activations