INDEX

Explanations

locations and addresses

oai_token-act-pair · gpt-3.5-turbo

names of places and locations

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

 synchronized

-0.83

 favors

-0.77

 flavors

-0.76

 realized

-0.75

 realize

-0.75

 unfavorable

-0.75

 favorable

-0.74

 salsa

-0.74

 flavorful

-0.74

 USPS

-0.73

POSITIVE LOGITS

shire

1.47

bourne

1.30

stown

1.28

mere

1.22

cliffe

1.21

 Vale

1.20

gow

1.18

borough

1.18

burgh

1.17

hire

1.17

Activations Density 0.246%

locations and addresses

names of places and locations

No Comments

No Known Activations