INDEX

Explanations

mentions of instant items or technology

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

umbing

-0.79

xual

-0.75

atche

-0.69

ramids

-0.69

llah

-0.68

ALD

-0.68

MET

-0.67

bard

-0.66

doctor

-0.66

tta

-0.65

POSITIVE LOGITS

aneously

2.07

aneous

1.49

 gratification

1.46

iation

1.38

iated

1.35

iating

1.23

iations

1.21

iate

1.12

 replay

1.11

iates

1.00

Activations Density 0.036%

mentions of instant items or technology

No Comments

No Known Activations