INDEX

Explanations

words related to destruction or strong actions

oai_token-act-pair · gpt-3.5-turbo

the end of sentences or paragraphs 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

 Niet

-0.69

 Frie

-0.61

 Vaugh

-0.59

Pru

-0.52

enegger

-0.52

 Leilan

-0.52

 Berm

-0.52

 Moroc

-0.50

 undermin

-0.50

 corrid

-0.50

POSITIVE LOGITS

\":

0.60

imum

0.49

ciples

0.48

phrine

0.48

cised

0.47

pedia

0.47

DragonMagazine

0.47

clinton

0.47

pret

0.46

âĦ¢:

0.46

Activations Density 0.390%

words related to destruction or strong actions

the end of sentences or paragraphs in the text

No Comments

No Known Activations