INDEX

Explanations

references to informational content or updates related to specific topics

oai_token-act-pair · gpt-3.5-turbo

references to media content and discussions around performance metrics

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

ARDIS

-0.56

earchers

-0.55

 misunder

-0.52

 Nobel

-0.52

 quotations

-0.52

 proverb

-0.51

ictionary

-0.51

 amuse

-0.50

 inventions

-0.50

illions

-0.50

POSITIVE LOGITS

Additionally

0.56

0.55

GG

0.53

DPS

0.52

>>\

0.50

 LGBTQ

0.50

HB

0.50

(#

0.50

 Twitch

0.50

âĶ

0.48

Activations Density 1.968%

references to informational content or updates related to specific topics

references to media content and discussions around performance metrics

No Comments

No Known Activations