INDEX

Explanations

European political figures and entities

oai_token-act-pair · gpt-3.5-turbo

references to officials and their roles within the European Union

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Chinatown

-0.98

 Manson

-0.92

 Arkansas

-0.90

 Mormon

-0.89

awar

-0.85

 Navajo

-0.85

 Mormons

-0.84

 Ranch

-0.81

 Plains

-0.79

 Aboriginal

-0.79

POSITIVE LOGITS

 Brussels

1.43

MEP

1.41

EU

1.40

EUR

1.39

euro

1.32

EU

1.28

 Luxembourg

1.24

 âĤ¬

1.24

Euro

1.23

 Stras

1.22

Activations Density 0.249%

European political figures and entities

references to officials and their roles within the European Union

No Comments

No Known Activations