INDEX

Explanations

phrases related to economic prosperity and financial support

oai_token-act-pair · gpt-3.5-turbo

terms related to prosperity and vulgarity

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

olkien

-0.83

Roy

-0.75

ORGE

-0.74

~~~~~~~~~~~~~~~~

-0.73

cham

-0.72

ERROR

-0.72

BOOK

-0.69

llan

-0.67

GAME

-0.66

chnology

-0.66

POSITIVE LOGITS

ity

2.84

ities

2.09

itous

1.46

ITY

1.41

itarian

1.36

itÃ©

1.34

ation

1.22

ITIES

1.20

iated

1.09

ification

1.08

Activations Density 0.083%

phrases related to economic prosperity and financial support

terms related to prosperity and vulgarity

No Known Activations