INDEX

Explanations

terminology related to symptom expressions in patients

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

DataPropertyName

-0.60

icitis

-0.59

-0.57

اریخ

-0.54

انگلیسی

-0.53

flikt

-0.52

toHave

-0.52

ğraf

-0.52

virons

-0.51

—

-0.51

POSITIVE LOGITS

Hozzáférés

0.63

 maît

0.59

AddTagHelper

0.57

ChildScrollView

0.57

 parlato

0.57

autonomie

0.57

 inability

0.54

 Bakan

0.54

>*/

0.53

 konuş

0.52

Activations Density 1.539%

terminology related to symptom expressions in patients

No Comments

No Known Activations