INDEX

Explanations

references to specific geographical locations

oai_token-act-pair · gpt-3.5-turbo

specific geographic or political locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Worldwide

-0.63

umble

-0.63

olphin

-0.63

WARD

-0.62

wards

-0.62

 rooting

-0.62

bed

-0.61

 marrow

-0.61

 chilling

-0.60

ioned

-0.60

POSITIVE LOGITS

È

1.24

³

1.16

Ļ

1.07

Ľ

1.05

ĺ

1.04

£

1.00

ł

0.99

ofer

0.97

¹

0.96

ĥ

0.95

Activations Density 0.007%

references to specific geographical locations

specific geographic or political locations

No Comments

No Known Activations