INDEX

Explanations

phrases that contain the letter "p" followed by a verb

oai_token-act-pair · gpt-3.5-turbo

words starting with the letter "p"

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

FTWARE

-0.87

æ©Ł

-0.86

 GOODMAN

-0.84

ãĤ´ãĥ³

-0.83

ãĤ¼ãĤ¦ãĤ¹

-0.83

 Realms

-0.78

MpServer

-0.76

é¾įåĸļå£«

-0.75

DragonMagazine

-0.74

ãĥĨ

-0.74

POSITIVE LOGITS

uffed

1.22

aired

1.15

airs

1.12

orter

1.06

ussy

1.04

orters

1.03

appy

1.03

ulse

1.02

uffs

1.02

ascal

1.01

Activations Density 0.038%

phrases that contain the letter "p" followed by a verb

words starting with the letter "p"

No Comments

No Known Activations