INDEX

Explanations

mentions of names that end in "-aur"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Kaur" and related variations

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

 Proced

-0.75

LINE

-0.71

 Shroud

-0.71

 CLSID

-0.69

 Grid

-0.66

 Clip

-0.64

CBI

-0.63

PC

-0.63

ABE

-0.62

 Perspective

-0.62

POSITIVE LOGITS

aur

1.46

issan

1.14

idon

1.09

ienne

0.99

isance

0.95

ua

0.89

uan

0.87

thur

0.87

antes

0.87

anamo

0.86

Activations Density 0.005%

mentions of names that end in "-aur"

occurrences of the word "Kaur" and related variations

No Comments

No Known Activations