INDEX

Explanations

dates and technological terms

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Tradable

-0.84

 Fisheries

-0.81

 Bound

-0.76

 Yuan

-0.74

 Sanctuary

-0.71

 Thrones

-0.68

 Ascend

-0.67

 Rift

-0.67

 Zombies

-0.67

 Patron

-0.66

POSITIVE LOGITS

detail

1.40

index

1.31

why

1.29

hillary

1.27

features

1.22

article

1.22

english

1.20

archives

1.18

show

1.18

report

1.17

Activations Density 0.038%

dates and technological terms

No Comments

No Known Activations