INDEX

Explanations

references to specific locations or people, such as "Sutherland Springs" and "Singer"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific locations and individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

boards

-0.88

oard

-0.80

FACE

-0.73

ble

-0.72

¥µ

-0.71

ipolar

-0.68

board

-0.68

ombo

-0.67

acious

-0.67

hist

-0.66

POSITIVE LOGITS

utherland

1.28

 Sutherland

1.23

ciating

0.94

bilt

0.89

nikov

0.88

emouth

0.84

cliffe

0.82

enegger

0.78

esson

0.77

IGHTS

0.77

Activations Density 0.021%

references to specific locations or people, such as "Sutherland Springs" and "Singer"

mentions of specific locations and individuals

No Comments

No Known Activations