INDEX

Explanations

mentions of nurses or nursing-related terms

oai_token-act-pair · gpt-3.5-turbo

references to nurses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

inations

-0.90

 Ramadan

-0.81

izoph

-0.77

çīĪ

-0.76

izons

-0.73

azeera

-0.71

ogh

-0.67

arta

-0.67

inates

-0.67

itious

-0.66

POSITIVE LOGITS

maid

1.41

 practitioner

1.33

 nurs

0.93

 nursing

0.89

 nurse

0.87

 examiner

0.84

 practitioners

0.83

 Nurs

0.77

ice

0.77

 lact

0.75

Activations Density 0.026%

mentions of nurses or nursing-related terms

references to nurses

No Comments

No Known Activations