INDEX

Explanations

mentions of social media actions or usernames

oai_token-act-pair · gpt-3.5-turbo

indications of social media engagement

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

 thrust

-0.79

etheless

-0.75

 tackling

-0.69

 penal

-0.68

 unsc

-0.68

 stewards

-0.66

arers

-0.64

tug

-0.64

 manoeuv

-0.64

 poisoning

-0.64

POSITIVE LOGITS

Associated

1.08

Follow

1.03

Anonymous

1.00

Original

0.98

FOR

0.98

OTHER

0.97

STER

0.94

EDIT

0.92

TOP

0.91

LET

0.90

Activations Density 0.062%

mentions of social media actions or usernames

indications of social media engagement

No Comments

No Known Activations