INDEX

Explanations

references to "DE" followed by a number

oai_token-act-pair · gpt-3.5-turbo

mentions of the abbreviation "DE" followed by numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 BaseType

-0.83

olulu

-0.82

toggle

-0.80

ãĤ¤ãĥĪ

-0.80

ocene

-0.78

ãĤ¹ãĥĪ

-0.78

uyomi

-0.77

ãĤ±

-0.76

oulos

-0.75

 è£ıè¦ļéĨĴ

-0.75

POSITIVE LOGITS

VICE

1.22

FAULT

1.16

FIN

1.08

ATH

1.01

POS

1.00

VEL

0.99

PUT

0.93

GE

0.90

FINE

0.88

VE

0.86

Activations Density 0.011%

references to "DE" followed by a number

mentions of the abbreviation "DE" followed by numbers

No Comments

No Known Activations