INDEX

Explanations

terms related to Canada

oai_token-act-pair · gpt-3.5-turbo

mentions of "Canadian" and related entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

mble

-0.86

hots

-0.86

bler

-0.84

atz

-0.81

oldemort

-0.81

itzer

-0.77

tle

-0.74

inse

-0.74

blers

-0.73

%]

-0.72

POSITIVE LOGITS

 Forces

1.19

 Tire

0.98

 Canadians

0.98

 Centre

0.97

 provinces

0.93

 Rockies

0.92

apolis

0.91

 Armed

0.87

 Broadcasting

0.87

 Affairs

0.83

Activations Density 0.013%

terms related to Canada

mentions of "Canadian" and related entities

No Comments

No Known Activations