INDEX

Explanations

mentions of political figures, government departments, and official statements in news articles

oai_token-act-pair · gpt-3.5-turbo

specific roles or titles related to government or official positions

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

 Madison

-0.77

 dime

-0.74

 Courtney

-0.74

 McKay

-0.73

 Vaughn

-0.71

 Michaels

-0.71

 Byrd

-0.71

 Doyle

-0.71

 Everett

-0.70

Madison

-0.70

POSITIVE LOGITS

 Rohingya

1.07

ÄŁ

1.03

ÅŁ

0.99

 Azerbai

0.93

 Malays

0.92

jriwal

0.91

 Sabha

0.90

 Myanmar

0.89

 Syri

0.88

 Kham

0.88

Activations Density 2.843%

mentions of political figures, government departments, and official statements in news articles

specific roles or titles related to government or official positions

No Comments

No Known Activations