INDEX

Explanations

words related to movement and physical actions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 GoPro

-0.68

 Fiesta

-0.68

Kids

-0.67

 Collider

-0.67

cial

-0.66

 Cassidy

-0.64

 Activities

-0.63

ggies

-0.62

 Environmental

-0.62

classic

-0.62

POSITIVE LOGITS

 thence

1.50

 forth

1.48

 hither

1.40

 upon

1.31

 unto

1.30

 thereto

1.20

 boldly

1.19

 anew

1.19

 irresist

1.13

 perpend

1.11

Activations Density 0.218%

words related to movement and physical actions

No Comments

No Known Activations