INDEX

Explanations

phrases related to buying or obtaining tickets

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ilic

-0.70

ogen

-0.68

natural

-0.66

hov

-0.66

 âĨĳ

-0.65

stant

-0.64

gha

-0.63

gru

-0.63

ishi

-0.61

Begin

-0.61

POSITIVE LOGITS

 tickets

3.87

 Tickets

2.95

 ticket

2.83

Tickets

2.62

 Ticket

2.39

ticket

2.11

 seats

1.71

ickets

1.60

 fares

1.50

 invitations

1.47

Activations Density 0.012%

phrases related to buying or obtaining tickets

No Comments

No Known Activations