INDEX

Explanations

mentions of the country "Canada."

oai_token-act-pair · gpt-3.5-turbo

mentions of "Canada."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

sym

-0.83

lihood

-0.78

bler

-0.75

ãĥł

-0.74

tle

-0.73

inse

-0.71

IU

-0.68

ļé

-0.68

stad

-0.68

bol

-0.68

POSITIVE LOGITS

 Goose

1.12

 Scotia

0.95

 Centre

0.92

 Canadians

0.90

 Revenue

0.89

 Tire

0.88

 Forces

0.83

 Skies

0.82

 Gazette

0.81

 Canada

0.81

Activations Density 0.018%

mentions of the country "Canada."

mentions of "Canada."

No Comments

No Known Activations