INDEX

Explanations

medical professionals, treatment procedures, and hospital admissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

terase

-0.57

 drep

-0.54

 éduc

-0.47

根

-0.46

 educativa

-0.44

enumi

-0.43

Benzene

-0.43

 commerce

-0.42

kom

-0.42

soy

-0.42

POSITIVE LOGITS

 hospital

1.50

 hospitals

1.35

 Hospital

1.28

 Hospitals

1.22

 HOSPITAL

1.21

hospital

1.19

Hospital

1.19

 hospitalized

1.14

 hospitalization

1.08

Hospitals

1.04

Activations Density 0.204%

medical professionals, treatment procedures, and hospital admissions

No Comments

No Known Activations