INDEX

Explanations

questions or exclamations containing question marks

oai_token-act-pair · gpt-3.5-turbo

questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 encount

-0.84

 colon

-0.71

avorite

-0.70

 charism

-0.68

apter

-0.66

respective

-0.66

alist

-0.65

outheast

-0.65

 paralle

-0.65

obos

-0.64

POSITIVE LOGITS

 Surely

1.12

 Somebody

1.09

 Where

1.07

 Anyway

1.05

Why

1.03

 Nope

1.01

 Certainly

0.96

Isn

0.96

 Probably

0.96

?!

0.95

Activations Density 0.103%

questions or exclamations containing question marks

questions

No Comments

No Known Activations