INDEX

Explanations

introductory phrases indicating a shift in topic or a new piece of information

oai_token-act-pair · gpt-3.5-turbo

the word "Here" as a signal for an introduction to various topics or lists

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

existent

-0.56

 absor

-0.56

Doctors

-0.55

 Archdemon

-0.55

nib

-0.55

)].

-0.55

 Circle

-0.54

mong

-0.54

 systemd

-0.54

 sshd

-0.54

POSITIVE LOGITS

tical

1.27

tics

1.26

abouts

1.20

tic

1.10

fore

0.82

upon

0.82

after

0.80

yers

0.79

 Comes

0.77

itia

0.77

Activations Density 0.034%

introductory phrases indicating a shift in topic or a new piece of information

the word "Here" as a signal for an introduction to various topics or lists

No Comments

No Known Activations