INDEX

Explanations

questions starting with the word "What"

oai_token-act-pair · gpt-3.5-turbo

inquiries about examples, choices, and the significance of various concepts

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

iHUD

-0.63

umbn

-0.61

hover

-0.58

ippi

-0.58

rency

-0.56

udging

-0.54

SU

-0.52

Sic

-0.52

mun

-0.52

ruciating

-0.51

POSITIVE LOGITS

!?

1.25

?!

1.25

1.21

?!"

1.21

 does

1.20

???

1.19

?"

1.16

 DOES

1.16

?????

1.15

!?"

1.12

Activations Density 0.066%

questions starting with the word "What"

inquiries about examples, choices, and the significance of various concepts

No Comments

No Known Activations