INDEX

Explanations

mentions of transportation-related terms, specifically focusing on trains and tunnel-related words

oai_token-act-pair · gpt-3.5-turbo

references to trains and transportation-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Hick

-0.83

 Carter

-0.68

oses

-0.66

 McGr

-0.65

resp

-0.63

 Barron

-0.63

 Bates

-0.63

 Clayton

-0.62

Hip

-0.62

HB

-0.62

POSITIVE LOGITS

train

2.98

tun

2.06

odon

1.23

TOR

1.16

wagen

1.07

uner

1.00

Train

1.00

ENG

0.97

 Levant

0.96

din

0.95

Activations Density 0.026%

mentions of transportation-related terms, specifically focusing on trains and tunnel-related words

references to trains and transportation-related terms

No Comments

No Known Activations