INDEX

Explanations

abbreviations or acronyms related to virtual machines

oai_token-act-pair · gpt-3.5-turbo

references to virtual machine technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alty

-0.90

 Flavoring

-0.82

 prevailing

-0.81

agher

-0.79

iflower

-0.78

alties

-0.75

ortment

-0.73

uten

-0.73

thritis

-0.72

baugh

-0.71

POSITIVE LOGITS

kernel

0.93

VM

0.92

GPU

0.90

MC

0.86

DAQ

0.86

OST

0.86

ware

0.83

HS

0.83

Protect

0.81

Admin

0.81

Activations Density 0.019%

abbreviations or acronyms related to virtual machines

references to virtual machine technology

No Comments

No Known Activations