INDEX

Explanations

phrases or words related to subjective judgments or opinions

oai_token-act-pair · gpt-3.5-turbo

complex phrases related to social issues and human experiences

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

arnaev

-0.61

 confir

-0.56

ĪĴ

-0.56

Pok

-0.54

ãĥ¯ãĥ³

-0.53

 Sorce

-0.53

arthed

-0.51

 Jagu

-0.51

Orig

-0.50

 streng

-0.50

POSITIVE LOGITS

".

2.29

",

2.22

"?

2.16

";

2.14

"!

2.09

2.02

":

2.01

"...

1.99

"âĢ¦

1.99

".[

1.98

Activations Density 0.481%

phrases or words related to subjective judgments or opinions

complex phrases related to social issues and human experiences

No Comments

No Known Activations