INDEX

Explanations

dates or periods related to weeks within contexts

oai_token-act-pair · gpt-3.5-turbo

references to specific weeks or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ashtra

-0.71

åĤ

-0.63

cellence

-0.60

utenant

-0.58

agles

-0.58

 Bruins

-0.58

omething

-0.58

awei

-0.58

âĢ¢âĢ¢

-0.58

itars

-0.58

POSITIVE LOGITS

days

1.49

night

1.27

DAY

1.04

lies

1.03

ends

1.02

end

0.92

END

0.92

stop

0.83

aday

0.83

long

0.79

Activations Density 0.088%

dates or periods related to weeks within contexts

references to specific weeks or time periods

No Comments

No Known Activations