INDEX

Explanations

proper nouns or acronyms with the word "AT" followed by a high activation score

oai_token-act-pair · gpt-3.5-turbo

the abbreviation "AT" and its various mentions throughout the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Tsukuyomi

-0.70

perse

-0.70

 Micha

-0.66

produ

-0.66

ingen

-0.63

dale

-0.62

Blade

-0.60

ãĥĭ

-0.60

place

-0.59

Ug

-0.59

POSITIVE LOGITS

ICAN

1.20

RON

0.99

itudes

0.95

ECH

0.95

RIC

0.94

TAIN

0.93

oday

0.93

ainment

0.92

htaking

0.91

hetically

0.90

Activations Density 0.007%

proper nouns or acronyms with the word "AT" followed by a high activation score

the abbreviation "AT" and its various mentions throughout the document

No Comments

No Known Activations