INDEX

Explanations

instances of the word "Mis" followed by another character or characters

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

 Schwarzenegger

-0.65

Ing

-0.63

JD

-0.62

 Guardians

-0.61

 Jehovah

-0.60

tc

-0.59

 Carbuncle

-0.59

 Bundy

-0.58

Aur

-0.57

 Bernard

-0.57

POSITIVE LOGITS

cellaneous

1.55

chief

1.34

ogyn

1.31

fortune

1.30

guided

1.17

cell

1.15

placed

1.14

beh

1.11

bah

1.07

leading

1.06

Activations Density 0.021%

instances of the word "Mis" followed by another character or characters

No Comments

No Known Activations