INDEX

Explanations

Twitter handles and online usernames

oai_token-act-pair · gpt-3.5-turbo

mentions of social media platforms or related handles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 condensed

-0.65

 bombard

-0.64

 intimidation

-0.62

 caring

-0.62

 memos

-0.62

 afore

-0.62

 loosely

-0.61

 condol

-0.61

 commuting

-0.61

 buildup

-0.61

POSITIVE LOGITS

Gh

1.24

Cu

1.22

OY

1.20

Ru

1.18

NK

1.17

RD

1.16

RN

1.16

qs

1.16

Tu

1.15

Ay

1.15

Activations Density 0.053%

Twitter handles and online usernames

mentions of social media platforms or related handles

No Comments

No Known Activations