INDEX

Explanations

the term "medical"

oai_token-act-pair · gpt-4-turbo

mentions of medical treatment or conditions

oai_token-act-pair · gpt-3.5-turbo

references to medical care and treatment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xual

-1.15

gger

-0.84

arget

-0.78

uble

-0.78

 Helpful

-0.71

 Wilde

-0.69

 Ramp

-0.69

unin

-0.68

adding

-0.68

auri

-0.67

POSITIVE LOGITS

 practition

1.04

 medical

0.96

 professionals

0.90

 marijuana

0.90

 practitioner

0.89

 care

0.89

 examiner

0.89

 doctor

0.89

 doctors

0.88

 physician

0.86

Activations Density 0.016%

the term "medical"

mentions of medical treatment or conditions

references to medical care and treatment

No Comments

No Known Activations