INDEX

Explanations

the verb "doesn't", followed by the contraction "'t", combined with a negative action or result

oai_token-act-pair · gpt-3.5-turbo

instances of the contraction "don't."

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

Negative Logits

ebus

-0.71

aminer

-0.68

 Seym

-0.66

 looms

-0.65

 imitation

-0.63

 buggy

-0.63

XT

-0.63

 mathemat

-0.63

 carbohyd

-0.62

 hemor

-0.62

POSITIVE LOGITS

ï¸ı

1.00

å¥³

0.93

×Ķ

0.91

ATH

0.89

Â·Â·

0.85

Â¯Â¯

0.84

Balt

0.83

ution

0.81

İ

0.80

âĸĦ

0.79

Activations Density 0.284%

the verb "doesn't", followed by the contraction "'t", combined with a negative action or result

instances of the contraction "don't."

No Known Activations