INDEX

Explanations

phrases related to statements or opinions within parentheses

oai_token-act-pair · gpt-3.5-turbo

the presence and frequency of parentheses in the text

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

wre

-0.77

 infring

-0.76

 lull

-0.75

 flee

-0.74

 inund

-0.73

 prey

-0.71

 tack

-0.71

 alley

-0.70

 evapor

-0.70

 smugglers

-0.69

POSITIVE LOGITS

pictured

1.43

excluding

1.35

?)

1.32

sic

1.30

including

1.30

formerly

1.29

via

1.28

!)

1.23

aka

1.23

again

1.22

Activations Density 0.155%

phrases related to statements or opinions within parentheses

the presence and frequency of parentheses in the text

No Comments

No Known Activations