INDEX

Explanations

mentions of nurses and related topics

oai_token-act-pair · gpt-3.5-turbo

mentions of the profession "nurse."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çīĪ

-0.90

arta

-0.72

inations

-0.72

AIN

-0.71

RFC

-0.69

Ùħ

-0.69

OPA

-0.68

upon

-0.67

izons

-0.66

Ø§ÙĦ

-0.65

POSITIVE LOGITS

maid

1.33

 practitioner

1.30

 nurse

1.11

 nurs

0.98

 examiner

0.94

 practitioners

0.89

 nursing

0.88

 nurses

0.88

 Nurs

0.85

 Nurse

0.81

Activations Density 0.007%

mentions of nurses and related topics

mentions of the profession "nurse."

No Comments

No Known Activations