INDEX

Explanations

phrases related to healthcare and social welfare policies

oai_token-act-pair · gpt-3.5-turbo

terms related to health insurance and healthcare policy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 adhesive

-0.71

Reviewer

-0.70

 suscept

-0.70

 magnification

-0.68

 largeDownload

-0.67

CV

-0.67

Publisher

-0.66

ocular

-0.65

 mascara

-0.63

 nesting

-0.63

POSITIVE LOGITS

 Australians

0.86

 Britons

0.85

 uninsured

0.84

 rural

0.82

 citizens

0.79

 everybody

0.78

 Americans

0.77

 impoverished

0.77

 Chattanooga

0.76

amacare

0.76

Activations Density 0.475%

phrases related to healthcare and social welfare policies

terms related to health insurance and healthcare policy

No Comments

No Known Activations