INDEX

Explanations

keywords related to settings and specifications of electronic devices

oai_token-act-pair · gpt-3.5-turbo

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

xious

-0.75

donald

-0.74

general

-0.71

tumblr

-0.71

yond

-0.71

phot

-0.71

ickr

-0.70

trump

-0.70

tmp

-0.70

ĻĤ

-0.69

POSITIVE LOGITS

 Theory

1.27

 Units

1.22

 Mode

1.22

 Disorder

1.21

 Initiative

1.20

 Agreement

1.20

 Framework

1.19

 Movement

1.18

 Syndrome

1.17

 Devices

1.16

Activations Density 0.354%

keywords related to settings and specifications of electronic devices

No Comments

No Known Activations