INDEX

Explanations

references to hospitals and hospitalization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-0.74

prehension

-0.74

WithMany

-0.73

NIR

-0.68

icle

-0.67

 hierogly

-0.67

 useEffect

-0.65

sz

-0.65

 Vend

-0.64

POSITIVE LOGITS

 hospital

1.19

 Hospital

1.14

hospital

1.09

 hospitals

1.08

 HOSPITAL

1.07

 Hospitals

1.03

Hospital

0.97

ospital

0.94

]();

0.88

 Hosp

0.85

Activations Density 0.062%

references to hospitals and hospitalization

No Comments

No Known Activations