INDEX

Explanations

terms related to healthcare practice and medical professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

存于互联网档案馆

-0.77

 EconPapers

-0.68

 AssemblyCulture

-0.62

žev

-0.61

idopsis

-0.60

IDENTAL

-0.57

 ویکی‌آمباردا

-0.57

URLException

-0.57

 Normdatei

-0.57

الحياه

-0.57

POSITIVE LOGITS

 patients

1.10

 patient

1.01

 clinical

0.97

 Patient

0.96

 Patients

0.96

 medical

0.95

 hospital

0.94

Patient

0.94

Patients

0.91

 clinicians

0.91

Activations Density 3.979%

terms related to healthcare practice and medical professionals

No Comments

No Known Activations