INDEX

Explanations

language related to giving or receiving instructions or advice

oai_token-act-pair · gpt-3.5-turbo

phrases or words indicating opportunities or offers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

entimes

-0.27

bably

-0.22

 Latino

-0.21

 Pruitt

-0.21

living

-0.21

 metabol

-0.21

]).

-0.20

 srfN

-0.20

quartered

-0.20

)]

-0.20

POSITIVE LOGITS

ombat

0.30

ebin

0.26

ngth

0.25

Ô

0.24

owship

0.24

DG

0.24

 Gamble

0.24

ADRA

0.23

 endeavour

0.23

awa

0.23

Activations Density 5.394%

language related to giving or receiving instructions or advice

phrases or words indicating opportunities or offers

No Comments

No Known Activations