INDEX

Explanations

phrases that suggest a cautionary message or negative outcome

oai_token-act-pair · gpt-3.5-turbo

symbols or specific characters that are not standard text

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Tanz

-0.74

 Brist

-0.74

Zup

-0.73

 Borough

-0.69

Osw

-0.69

enegger

-0.68

Tid

-0.67

 comprom

-0.67

 fortun

-0.65

 horizont

-0.64

POSITIVE LOGITS

¬

1.23

Ļ

1.19

ª

1.11

Â¢

1.07

ħ

1.07

ĸ

1.05

Ĵ

1.03

ı

1.00

¤

1.00

¡

0.99

Activations Density 0.468%

phrases that suggest a cautionary message or negative outcome

symbols or specific characters that are not standard text

No Comments

No Known Activations