INDEX

Explanations

mentions related to Canada

oai_token-act-pair · gpt-3.5-turbo

references to Canada and Canadian entities

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

bler

-0.80

inse

-0.73

ultan

-0.72

terior

-0.68

lihood

-0.66

sym

-0.65

swick

-0.64

gered

-0.63

blers

-0.63

%]

-0.63

POSITIVE LOGITS

 Tire

1.17

 Goose

1.14

 Scotia

0.99

 Centre

0.98

 Canadians

0.96

 Forces

0.96

Canada

0.95

 Trudeau

0.94

 Revenue

0.93

 aboriginal

0.93

Activations Density 0.042%

mentions related to Canada

references to Canada and Canadian entities

No Comments

No Known Activations