INDEX

Explanations

terms related to the medical field 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

躇

-0.75

Izvori

-0.71

 تضيفلها

-0.69

 mergeFrom

-0.64

 <=",

-0.62

 Dishwasher

-0.59

 ErrIntOverflow

-0.57

 profonda

-0.55

 propOrder

-0.54

 tremp

-0.54

POSITIVE LOGITS

 healthcare

1.12

 medical

1.08

 Healthcare

1.01

 health

0.99

 Medical

0.95

Healthcare

0.95

🏥

0.94

 hospitals

0.94

healthcare

0.93

 Health

0.93

Activations Density 0.744%

terms related to the medical field and healthcare

No Comments

No Known Activations