INDEX

Explanations

questions ending with question marks

oai_token-act-pair · gpt-3.5-turbo

questions and inquiries regarding various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tesy

-0.75

itely

-0.71

 quir

-0.69

 exclusively

-0.68

ady

-0.67

agen

-0.66

ensibly

-0.65

ciplinary

-0.65

iber

-0.64

lam

-0.64

POSITIVE LOGITS

 Lastly

1.25

 Finally

1.16

 Whatever

1.05

 Flavoring

0.98

 Conversely

0.98

etc

0.97

etc

0.96

 Eventually

0.95

Et

0.95

And

0.94

Activations Density 0.428%

questions ending with question marks

questions and inquiries regarding various topics

No Comments

No Known Activations