INDEX

Explanations

references to hospitals and medical care settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

bootstrapcdn

-0.79

complexContent

-0.77

WithMany

-0.75

 تضيفلها

-0.74

 hierogly

-0.70

 useEffect

-0.69

prehension

-0.68

躇

-0.68

 WebDriverWait

-0.67

 jLabel

-0.67

POSITIVE LOGITS

 hospital

1.59

 Hospital

1.53

hospital

1.42

 hospitals

1.39

Hospital

1.34

 Hospitals

1.32

 HOSPITAL

1.32

ospital

1.12

 hospitalization

1.08

Hospitals

1.06

Activations Density 0.037%

references to hospitals and medical care settings

No Comments

No Known Activations