INDEX

Explanations

keywords related to the Canadian Prime Minister, Justin Trudeau

oai_token-act-pair · gpt-3.5-turbo

mentions of Justin Trudeau

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

iHUD

-0.82

âĵĺ

-0.78

oxide

-0.78

bler

-0.75

×Ļ

-0.75

Ö¼

-0.75

×ĳ

-0.73

PsyNetMessage

-0.73

ASED

-0.72

×Ļ×

-0.70

POSITIVE LOGITS

udeau

1.31

 Trudeau

1.27

 Jinping

0.88

ipeg

0.84

 shenan

0.83

 Liberals

0.78

 Canad

0.77

oleon

0.75

bourg

0.75

eworthy

0.74

Activations Density 0.005%

keywords related to the Canadian Prime Minister, Justin Trudeau

mentions of Justin Trudeau

No Comments

No Known Activations