INDEX

Explanations

terms related to medical terminologies and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

-1.05

-0.86

providedIn

-0.78

awtextra

-0.77

 viewType

-0.68

harusnya

-0.63

 Nazar

-0.62

Portale

-0.61

 xenia

-0.60

IntoConstraints

-0.60

POSITIVE LOGITS

 patient

0.88

 patients

0.79

patient

0.76

 clinical

0.74

Patient

0.73

 Clinical

0.72

 Patient

0.71

 Patients

0.69

 clinicians

0.68

 CLINICAL

0.68

Activations Density 0.709%

terms related to medical terminologies and organizations

No Comments

No Known Activations