INDEX

Explanations

words related to various types of jackets

oai_token-act-pair · gpt-3.5-turbo

references to jackets and outerwear

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

rians

-0.78

minist

-0.68

mony

-0.67

rian

-0.67

tics

-0.64

Redd

-0.64

KNOWN

-0.64

raction

-0.64

mission

-0.64

ASY

-0.63

POSITIVE LOGITS

 jacket

1.32

 jackets

1.26

 Jacket

1.15

 sleeves

1.03

 coats

1.02

 sleeve

1.01

 coat

0.91

 sweater

0.90

 worn

0.90

 Jackets

0.83

Activations Density 0.007%

words related to various types of jackets

references to jackets and outerwear

No Comments

No Known Activations