INDEX

Explanations

keywords and phrases related to international news and events

oai_token-act-pair · gpt-3.5-turbo

phrases associated with significant numerical statistics or ratings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 initi

-0.73

 coron

-0.69

 Flame

-0.63

 experien

-0.63

 mosqu

-0.63

 enchanted

-0.63

 abused

-0.62

 Reincarnated

-0.62

 fors

-0.62

 regener

-0.62

POSITIVE LOGITS

Minor

1.00

Meanwhile

0.95

Related

0.94

Sensor

0.91

Few

0.91

Others

0.90

Prof

0.90

Spain

0.90

Similar

0.88

TAG

0.88

Activations Density 0.136%

keywords and phrases related to international news and events

phrases associated with significant numerical statistics or ratings

No Comments

No Known Activations