INDEX

Explanations

terms related to the Affordable Care Act

oai_token-act-pair · gpt-3.5-turbo

references to the Affordable Care Act (ACA)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 circles

-0.77

 sheep

-0.69

den

-0.67

 tails

-0.67

po

-0.65

 rever

-0.65

 pits

-0.64

dev

-0.64

po

-0.63

 pupils

-0.63

POSITIVE LOGITS

 Affordable

3.64

ACA

2.05

 Obamacare

1.74

 ObamaCare

1.55

ordable

1.54

 uninsured

1.46

 affordable

1.41

amacare

1.36

 affordability

1.29

 Patient

1.25

Activations Density 0.016%

terms related to the Affordable Care Act

references to the Affordable Care Act (ACA)

No Comments

No Known Activations