INDEX

Explanations

instances where elements appear in both the front and back of something

oai_token-act-pair · gpt-3.5-turbo

references to positions or locations in diagrams or descriptions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Deal

-0.78

TIME

-0.77

-0.76

EStream

-0.70

faith

-0.68

Time

-0.67

Merit

-0.67

ãĥīãĥ©

-0.66

Hero

-0.65

ãģ®éŃĶ

-0.65

POSITIVE LOGITS

 underside

1.63

 bottom

1.48

 exterior

1.33

 rear

1.31

 interior

1.29

 sides

1.29

 upper

1.28

 corners

1.25

 outer

1.24

bottom

1.23

Activations Density 0.211%

instances where elements appear in both the front and back of something

references to positions or locations in diagrams or descriptions

No Comments

No Known Activations