INDEX

Explanations

mentions of nurses

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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.83

çīĪ

-0.80

izons

-0.74

eering

-0.71

inates

-0.69

ãĥĪ

-0.66

DX

-0.66

 Ramadan

-0.65

obo

-0.65

oric

-0.65

POSITIVE LOGITS

maid

1.36

 practitioner

1.34

 nurs

1.01

 examiner

0.97

 nurse

0.96

 Nurs

0.94

 practitioners

0.89

 nursing

0.83

 nurses

0.80

erest

0.77

Activations Density 0.012%

mentions of nurses

references to nurses

No Comments

No Known Activations