INDEX

Explanations

phrases related to covering a wide range of topics or issues

oai_token-act-pair · gpt-3.5-turbo

phrases indicating variety or range in contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

cknowled

-0.75

appointed

-0.64

Winged

-0.64

 acquies

-0.63

aeus

-0.62

 largeDownload

-0.62

 Syri

-0.62

 embold

-0.61

 ashamed

-0.61

ĪĴ

-0.60

POSITIVE LOGITS

 topics

1.27

 situations

1.21

 aspects

1.16

 scenarios

1.10

 tasks

1.09

 genres

1.08

 types

1.08

 kinds

1.07

 domains

1.03

 categories

1.02

Activations Density 0.293%

phrases related to covering a wide range of topics or issues

phrases indicating variety or range in contexts

No Comments

No Known Activations