INDEX

Explanations

phrases related to locations such as cities, countries, businesses, or geographical features

oai_token-act-pair · gpt-3.5-turbo

instances of the word "including" and phrases related to significant global issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

enary

-0.73

orem

-0.68

inar

-0.66

irie

-0.65

riage

-0.64

sburg

-0.63

ery

-0.61

ISION

-0.61

uto

-0.60

ulus

-0.60

POSITIVE LOGITS

 although

1.23

 albeit

1.20

 including

1.18

 includ

1.12

 culminating

1.09

 whereas

1.07

 notably

1.06

but

1.01

 though

1.00

 prompting

0.98

Activations Density 0.402%

phrases related to locations such as cities, countries, businesses, or geographical features

instances of the word "including" and phrases related to significant global issues

No Comments

No Known Activations