INDEX

Explanations

language related to requests or instructions, such as asking for tips, making submissions, or leaving comments

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating the sharing or requesting of information and feedback

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

psc

-0.86

gdala

-0.76

artisan

-0.76

iably

-0.75

itone

-0.74

obyl

-0.72

©¶æ¥µ

-0.70

ibr

-0.69

olate

-0.68

gado

-0.68

POSITIVE LOGITS

 tips

1.28

 announcements

1.25

 explanations

1.23

 tutorials

1.22

 recommendations

1.22

 suggestions

1.21

 endorsements

1.20

 corrections

1.15

 additions

1.13

 screenshots

1.13

Activations Density 0.165%

language related to requests or instructions, such as asking for tips, making submissions, or leaving comments

conjunctions and phrases indicating the sharing or requesting of information and feedback

No Comments

No Known Activations