INDEX

Explanations

references to healthcare-related phrases and policies related to health insurance plans and coverage

oai_token-act-pair · gpt-3.5-turbo

references to health insurance policies and their related coverage

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 IMAGES

-0.74

Hoo

-0.73

 encount

-0.72

cia

-0.72

lins

-0.72

oder

-0.71

ovie

-0.70

ograp

-0.69

onnaissance

-0.66

 Verb

-0.66

POSITIVE LOGITS

 premiums

1.03

amacare

0.99

 eligibility

0.96

 uninsured

0.95

 providers

0.95

 rebate

0.94

 Advantage

0.93

 provider

0.89

holders

0.88

 Marketplace

0.86

Activations Density 0.103%

references to healthcare-related phrases and policies related to health insurance plans and coverage

references to health insurance policies and their related coverage

No Comments

No Known Activations