INDEX

Explanations

terms related to Parkinson's disease and associated medical terminology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.67

WebVitals

-0.63

</table>

-0.61

Biographie

-0.61

ed

-0.60

/*

-0.58

ه

-0.58

ete

-0.58

toPromise

-0.57

 whole

-0.57

POSITIVE LOGITS

ded

0.96

ding

0.78

DDDD

0.76

dddd

0.74

DDD

0.72

DED

0.70

 unknownFields

0.70

died

0.70

 faſt

0.68

BUD

0.68

Activations Density 1.209%

terms related to Parkinson's disease and associated medical terminology

No Comments

No Known Activations