INDEX

Explanations

phrases related to healthcare coverage, insurance, and the uninsured

oai_token-act-pair · gpt-3.5-turbo

terms related to insurance status, particularly focusing on the uninsured

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

OTE

-0.84

 Rapp

-0.81

nan

-0.77

ovie

-0.76

azine

-0.74

OPA

-0.73

wcsstore

-0.71

AMS

-0.70

ames

-0.68

EFF

-0.68

POSITIVE LOGITS

 uninsured

1.17

insured

0.77

 mortality

0.75

ordable

0.75

 premiums

0.73

 carriers

0.70

uates

0.69

 coverage

0.69

 insured

0.68

 insurance

0.66

Activations Density 0.006%

phrases related to healthcare coverage, insurance, and the uninsured

terms related to insurance status, particularly focusing on the uninsured

No Comments

No Known Activations