INDEX

Explanations

medical terms and health-related information

oai_token-act-pair · gpt-3.5-turbo

concerns related to health conditions and their management

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Franch

-0.85

Untitled

-0.69

apult

-0.64

Flags

-0.64

Artist

-0.64

xtap

-0.64

çīĪ

-0.64

Contract

-0.63

 Voting

-0.63

 scoreboard

-0.62

POSITIVE LOGITS

 symptoms

1.33

 hormonal

1.30

 medications

1.29

 Symptoms

1.27

 physiological

1.26

 dietary

1.26

 physi

1.25

 patients

1.24

 clinical

1.23

 hormone

1.22

Activations Density 1.058%

medical terms and health-related information

concerns related to health conditions and their management

No Known Activations