INDEX

Explanations

locations or places mentioned in Florida (Fla)

oai_token-act-pair · gpt-3.5-turbo

references to the state of Florida

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sticks

-0.82

lords

-0.76

small

-0.76

stick

-0.76

guard

-0.75

BOOK

-0.73

geist

-0.72

ä¸Ģ

-0.69

LESS

-0.69

selves

-0.68

POSITIVE LOGITS

herty

1.11

ignt

1.07

Fla

1.03

issance

1.00

cffff

0.88

apon

0.84

uthor

0.83

overe

0.80

endas

0.78

adelphia

0.77

Activations Density 0.004%

locations or places mentioned in Florida (Fla)

references to the state of Florida

No Comments

No Known Activations