INDEX

Explanations

mentions of reservations, particularly related to making, having, or expressing them

oai_token-act-pair · gpt-3.5-turbo

words related to reservations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utenberg

-0.76

obs

-0.73

ogg

-0.71

redd

-0.71

chie

-0.71

src

-0.68

sonian

-0.68

moving

-0.67

berman

-0.67

ramid

-0.67

POSITIVE LOGITS

 reservation

1.30

 reservations

1.28

 Reserv

0.94

ervation

0.81

 tickets

0.75

aste

0.73

irmation

0.73

erv

0.71

 Restaur

0.71

 booking

0.69

Activations Density 0.006%

mentions of reservations, particularly related to making, having, or expressing them

words related to reservations

No Comments

No Known Activations