INDEX

Explanations

mentions of authority figures and their actions

oai_token-act-pair · gpt-3.5-turbo

tokens that signify the end of content or transitions in text

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

 Azerb

-0.05

elsius

-0.04

Þ

-0.04

 guiActiveUn

-0.04

oÄŁ

-0.04

ĳå£«

-0.04

ñ

-0.04

ĪĴ

-0.04

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.04

£ı

-0.04

POSITIVE LOGITS

↵

0.06

0.05

the

0.05

and

0.05

The

0.05

in

0.04

to

0.04

Activations Density 2.220%

mentions of authority figures and their actions

tokens that signify the end of content or transitions in text

No Comments

No Known Activations