INDEX

Explanations

words related to faith or belief

oai_token-act-pair · gpt-3.5-turbo

mentions of infidelity and unfaithfulness

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

Negative Logits

 Bett

-0.83

 Gloves

-0.71

Roz

-0.67

 goggles

-0.67

taboola

-0.67

 Rasm

-0.65

 Klaus

-0.64

 Papers

-0.63

 Mouse

-0.63

ATA

-0.62

POSITIVE LOGITS

vironment

1.13

ryu

0.92

akespeare

0.91

peror

0.85

olitics

0.85

abol

0.84

xual

0.84

uncture

0.83

metics

0.80

stall

0.80

Activations Density 0.040%

words related to faith or belief

mentions of infidelity and unfaithfulness

No Known Activations