INDEX

Explanations

phrases related to community involvement and social contributions

oai_token-act-pair · gpt-3.5-turbo

discussions around inclusion and contributions to society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iple

-0.52

çĶ°

-0.51

Nit

-0.51

amount

-0.50

 largeDownload

-0.49

SourceFile

-0.49

 Converted

-0.48

Strike

-0.47

DragonMagazine

-0.47

ortium

-0.46

POSITIVE LOGITS

equality

0.57

 paycheck

0.55

 anymore

0.53

 frivolous

0.52

 cheaply

0.51

 anytime

0.50

or

0.50

 advantageous

0.50

 oneself

0.49

 disadvantaged

0.49

Activations Density 2.288%

phrases related to community involvement and social contributions

discussions around inclusion and contributions to society

No Comments

No Known Activations