INDEX

Explanations

phrases related to political actions and government policies

oai_token-act-pair · gpt-3.5-turbo

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

onica

-0.79

tale

-0.76

hedon

-0.75

ONY

-0.71

Ars

-0.69

VALUE

-0.69

ÑĮ

-0.67

 Mayhem

-0.67

 Guilty

-0.67

beh

-0.67

POSITIVE LOGITS

 defund

1.31

 abolish

1.31

 privat

1.30

 abol

1.25

 overhaul

1.24

 repeal

1.22

 repealing

1.21

 eliminate

1.19

 curtail

1.15

 eliminating

1.12

Activations Density 0.367%

phrases related to political actions and government policies

No Comments

No Known Activations