INDEX

Explanations

phrases related to the Department of Health and Human Services

oai_token-act-pair · gpt-3.5-turbo

references to health and human services organizations

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

ysis

-0.75

alogue

-0.73

yond

-0.71

cause

-0.71

weight

-0.71

ÅŁ

-0.71

reads

-0.70

phrine

-0.69

proof

-0.69

ãĥ£

-0.69

POSITIVE LOGITS

 Agency

1.22

 Administration

1.18

 Loan

0.99

 Employees

0.95

 Commission

0.91

 Organizations

0.91

 Committee

0.91

 Administ

0.87

 Assistance

0.86

 Services

0.85

Activations Density 0.034%

phrases related to the Department of Health and Human Services

references to health and human services organizations

No Comments

No Known Activations