INDEX

Explanations

mentions of the word "reservation."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "reservation" and its variations

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

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

 Faust

-0.76

cia

-0.69

iframe

-0.69

Dot

-0.68

rod

-0.68

ibel

-0.67

fo

-0.66

Cy

-0.65

Ty

-0.65

Cy

-0.63

POSITIVE LOGITS

 reservation

4.16

 reservations

4.12

 Reserv

2.04

 reserve

1.50

 reserv

1.44

 reserved

1.30

 booking

1.21

 concession

1.18

 quota

1.14

ervation

1.13

Activations Density 0.021%

mentions of the word "reservation."

occurrences of the word "reservation" and its variations

No Comments

No Known Activations