INDEX

Explanations

technical terms related to medical imaging and examinations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

ha

-0.46

 code

-0.46

 solicit

-0.44

uan

-0.42

how

-0.42

tar

-0.42

chip

-0.41

vog

-0.41

UrlResolution

-0.40

othelial

-0.40

POSITIVE LOGITS

بوابة

0.74

GEBURTSDATUM

0.74

 Jefus

0.73

 يتيمه

0.72

 Majefty

0.72

 quæ

0.70

 purpoſe

0.69

awaiter

0.69

sidemargin

0.67

 Reſ

0.67

Activations Density 2.092%

technical terms related to medical imaging and examinations

No Comments

No Known Activations