INDEX

Explanations

sentences ending with a full stop

oai_token-act-pair · gpt-3.5-turbo

complete sentences

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

¥ŀ

-0.84

 volunte

-0.77

 nodd

-0.73

 prosec

-0.72

 encount

-0.71

 suspic

-0.70

 confir

-0.68

 rall

-0.67

yip

-0.67

 advoc

-0.66

POSITIVE LOGITS

My

1.71

My

1.60

1.56

1.43

my

1.31

 myself

1.21

 Whenever

1.17

 Somehow

1.17

my

1.16

MY

1.15

Activations Density 0.545%

sentences ending with a full stop

complete sentences

No Comments

No Known Activations