INDEX

Explanations

mentions or references to the name "Ron Paul"

oai_token-act-pair · gpt-3.5-turbo

mentions of Ron Paul

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Clean

-0.73

cyl

-0.68

Commercial

-0.68

Production

-0.66

 lodge

-0.65

Company

-0.64

 extraction

-0.64

âĸ¬

-0.63

Limit

-0.63

Disclaimer

-0.62

POSITIVE LOGITS

sburg

1.03

roud

0.95

 supporters

0.92

istan

0.89

atoon

0.86

sonian

0.84

isphere

0.83

ivas

0.83

sen

0.82

son

0.81

Activations Density 0.009%

mentions or references to the name "Ron Paul"

mentions of Ron Paul

No Comments

No Known Activations