INDEX

Explanations

words related to healthcare policy and the Affordable Care Act

oai_token-act-pair · gpt-3.5-turbo

references to the Affordable Care Act

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

NK

-0.79

KEN

-0.79

ns

-0.72

IGN

-0.72

ãĥĥãĥī

-0.71

RAF

-0.70

DN

-0.69

 Gerrard

-0.68

 MacDonald

-0.68

NW

-0.68

POSITIVE LOGITS

amacare

1.06

care

0.99

taker

0.93

payer

0.85

haar

0.84

 providers

0.81

Care

0.80

atism

0.78

 Provider

0.78

ternity

0.78

Activations Density 0.015%

words related to healthcare policy and the Affordable Care Act

references to the Affordable Care Act

No Comments

No Known Activations