INDEX

Explanations

references to hospitals and hospital-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 تضيفلها

-0.75

bootstrapcdn

-0.72

 hierogly

-0.72

WithMany

-0.71

prehension

-0.71

 grits

-0.67

NIR

-0.66

 vendus

-0.65

 Eust

-0.64

 useEffect

-0.64

POSITIVE LOGITS

 hospital

1.35

 Hospital

1.29

 hospitals

1.19

hospital

1.19

 HOSPITAL

1.13

 Hospitals

1.10

Hospital

1.08

ospital

1.00

 Hosp

0.90

 hospitalization

0.89

Activations Density 0.041%

references to hospitals and hospital-related terms

No Comments

No Known Activations