INDEX

Explanations

references to the United States

oai_token-act-pair · gpt-3.5-turbo

references to the United States

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bably

-0.72

rette

-0.68

lets

-0.67

antly

-0.65

lihood

-0.64

 McCartney

-0.63

 Ernst

-0.62

ozyg

-0.62

ously

-0.61

 Scand

-0.61

POSITIVE LOGITS

GS

1.21

AAF

1.16

ADA

1.09

MC

1.07

1.05

 Embassy

1.01

 embassy

1.00

NI

0.98

FK

0.97

UAL

0.94

Activations Density 0.061%

references to the United States

references to the United States

No Comments

No Known Activations