INDEX

Explanations

terms related to healthcare and health issues

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

 Kitten

-0.88

 Dickerson

-0.81

mno

-0.79

 Kör

-0.78

 Ceremonies

-0.78

PTSD

-0.78

 Spectroscopy

-0.76

 Showroom

-0.76

 Testament

-0.76

Kus

-0.76

POSITIVE LOGITS

 health

1.53

 Health

1.48

Health

1.37

health

1.37

HEALTH

1.31

 HEALTH

1.21

 Heath

1.11

 heath

1.05

Heath

1.04

健康

0.94

Activations Density 0.058%

terms related to healthcare and health issues

No Comments

No Known Activations