INDEX

Explanations

technical terms related to software updates and computer settings

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

jah

-0.63

knit

-0.62

incerity

-0.62

 Witt

-0.61

 Mills

-0.60

 circus

-0.60

raising

-0.58

letters

-0.57

akespeare

-0.57

 seminar

-0.56

POSITIVE LOGITS

 uninstall

1.45

 firmware

1.22

 install

1.21

 Windows

1.20

 Install

1.17

 BIOS

1.16

 installs

1.14

 Disable

1.14

installed

1.13

 installed

1.12

Activations Density 0.868%

technical terms related to software updates and computer settings

No Comments

No Known Activations