INDEX

Explanations

references to the word "Cat"

oai_token-act-pair · gpt-3.5-turbo

references to a character or concept involving "Cat."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mble

-0.84

demand

-0.78

htt

-0.74

byter

-0.73

gur

-0.70

ItemTracker

-0.69

ĺħ

-0.69

 Vaugh

-0.69

 Seym

-0.68

 plur

-0.67

POSITIVE LOGITS

aclysm

1.38

apult

1.20

Cat

1.15

cat

1.08

Cat

1.08

cats

0.97

bat

0.97

heter

0.91

fish

0.91

idon

0.89

Activations Density 0.005%

references to the word "Cat"

references to a character or concept involving "Cat."

No Comments

No Known Activations