INDEX

Explanations

terminology related to clinical contexts and healthcare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 للمعارف

-0.85

 élector

-0.80

 Gabriella

-0.79

popper

-0.77

 odeur

-0.76

InSection

-0.74

 CreateTagHelper

-0.71

Pp

-0.70

enoid

-0.69

ulados

-0.69

POSITIVE LOGITS

 Klin

0.91

 Clin

0.86

Clin

0.86

 clin

0.85

clin

0.80

<h3>

0.76

CLINICAL

0.73

 CLIN

0.73

Portale

0.71

 clinics

0.70

Activations Density 0.064%

terminology related to clinical contexts and healthcare

No Comments

No Known Activations