INDEX

Explanations

phrases and terms related to emergency situations and medical responses

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

Negative Logits

Vidite

-0.81

ստ

-0.75

rimid

-0.73

ynb

-0.73

grà

-0.70

 onPage

-0.70

󠁿

-0.69

lactin

-0.68

WSTR

-0.68

 виправивши

-0.66

POSITIVE LOGITS

 emergency

2.26

 Emergency

2.16

Emergency

2.03

emergency

1.98

 emergencies

1.93

 EMERGENCY

1.91

EMERGENCY

1.82

 Emer

1.36

 emergencia

1.36

紧急

1.22

Activations Density 0.080%

phrases and terms related to emergency situations and medical responses

No Known Activations