INDEX

Explanations

references to healthcare professionals and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 šķ

-0.54

hena

-0.52

 mensaj

-0.51

 commerciaux

-0.50

 énergétique

-0.49

 énergé

-0.49

 extré

-0.48

 procesos

-0.48

 perdu

-0.48

 trésor

-0.48

POSITIVE LOGITS

 doctors

1.31

 doctor

1.29

 Doctors

1.20

 physician

1.19

 physicians

1.19

Doctors

1.17

 Physician

1.14

 Physicians

1.14

 DOCTOR

1.12

doctor

1.11

Activations Density 0.375%

references to healthcare professionals and their roles

No Comments

No Known Activations