INDEX

Explanations

derogatory and offensive language

oai_token-act-pair · gpt-3.5-turbo

phrases expressing frustration or demands

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

iHUD

-0.76

Located

-0.73

[|

-0.70

catentry

-0.69

srf

-0.69

ipment

-0.69

pleted

-0.67

Initial

-0.67

Location

-0.66

 Â¥

-0.64

POSITIVE LOGITS

 hypocrisy

1.21

 feminists

1.16

 liberals

1.15

 hypocritical

1.14

 feminism

1.05

 leftists

1.03

 libertarians

1.00

 hypocr

0.99

 Chomsky

0.98

 Orwell

0.95

Activations Density 1.556%

derogatory and offensive language

phrases expressing frustration or demands

No Comments

No Known Activations