INDEX

Explanations

mentions of "health" and related terms

oai_token-act-pair · gpt-3.5-turbo

mention of health-related topics or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

xual

-0.81

yip

-0.79

 Helpful

-0.76

 Reloaded

-0.75

arget

-0.73

 Downing

-0.71

toe

-0.70

Duo

-0.70

 Darkness

-0.69

selves

-0.68

POSITIVE LOGITS

care

1.22

 care

1.21

 Care

1.04

 insurance

1.02

Care

1.01

iest

0.95

aceutical

0.92

amacare

0.91

 insurer

0.90

 insurers

0.90

Activations Density 0.031%

mentions of "health" and related terms

mention of health-related topics or issues

No Comments

No Known Activations