INDEX

Explanations

mentions of specific names or handles in a conversation or text

oai_token-act-pair · gpt-3.5-turbo

references and discussions related to political figures and events

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

Ð´

-0.88

cel

-0.85

Ì

-0.83

ÑĤ

-0.82

 Sloven

-0.82

Li

-0.82

 selfies

-0.80

Ð»

-0.79

 Lithuan

-0.78

Unity

-0.78

POSITIVE LOGITS

 Bush

2.22

Bush

2.08

bush

1.52

 Cheney

1.32

 bush

1.31

 George

1.27

Jeb

1.23

 Rove

1.20

 Gore

1.20

 Saddam

1.14

Activations Density 0.328%

mentions of specific names or handles in a conversation or text

references and discussions related to political figures and events

No Comments

No Known Activations