INDEX

Explanations

references to medical and healthcare-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 StringTokenizer

-0.44

 Catalytic

-0.43

Eig

-0.43

 automate

-0.42

 extinción

-0.41

 SURFACE

-0.41

 PARKING

-0.40

 felicitación

-0.40

 behave

-0.40

 devoirs

-0.39

POSITIVE LOGITS

 health

1.12

 medical

1.05

 Health

1.01

Health

0.97

 healthcare

0.95

health

0.90

 medically

0.89

medical

0.89

 Medical

0.85

Medical

0.84

Activations Density 0.963%

references to medical and healthcare-related topics

No Comments

No Known Activations