INDEX

Explanations

phrases related to the movement or transfer of something

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ifications

-0.66

 irrad

-0.65

 scratched

-0.65

DonaldTrump

-0.64

azo

-0.64

 Schwarzenegger

-0.64

Bav

-0.62

ises

-0.61

SAY

-0.61

andals

-0.59

POSITIVE LOGITS

chart

1.45

through

0.97

stream

0.95

flow

0.90

lining

0.88

 flows

0.85

cyt

0.84

 flowing

0.84

ey

0.81

flows

0.81

Activations Density 0.073%

phrases related to the movement or transfer of something

No Comments

No Known Activations