INDEX

Explanations

location names embedded in news articles

oai_token-act-pair · gpt-3.5-turbo

references to political and military events in Afghanistan

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Saturn

-0.86

 Daytona

-0.86

 Mercer

-0.83

ESA

-0.83

Disney

-0.82

byss

-0.82

Elsa

-0.82

 Pelicans

-0.80

 Charlotte

-0.79

 Asheville

-0.79

POSITIVE LOGITS

 Pakistan

2.25

 Pakistani

2.21

Pakistan

2.17

 Islamabad

2.17

 Karachi

1.96

 Taliban

1.95

 Kabul

1.91

 Afghan

1.90

Pak

1.84

 Kashmir

1.72

Activations Density 0.294%

location names embedded in news articles

references to political and military events in Afghanistan

No Comments

No Known Activations