INDEX

Explanations

proper nouns or named entities

oai_token-act-pair · gpt-3.5-turbo

tokens indicating the end of a document or section

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

CPR

-0.69

 crib

-0.66

 Ribbon

-0.64

 psycho

-0.63

 unrestricted

-0.63

 Strip

-0.62

 stressed

-0.61

 Triangle

-0.60

tops

-0.60

 Proto

-0.60

POSITIVE LOGITS

ixty

1.40

olutions

1.32

omew

1.32

ESSION

1.29

atisf

1.28

ierra

1.28

ometime

1.28

atellite

1.27

ustain

1.26

essions

1.23

Activations Density 0.052%

proper nouns or named entities

tokens indicating the end of a document or section

No Comments

No Known Activations