INDEX

Explanations

technical terms and acronyms related to technology and industry

oai_token-act-pair · gpt-3.5-turbo

references to government or technical entities, standards, or equipment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

hillary

-0.83

bnb

-0.74

neapolis

-0.70

terday

-0.69

abil

-0.69

atform

-0.68

vind

-0.65

-+-+

-0.64

ocious

-0.64

ottesville

-0.64

POSITIVE LOGITS

 logo

0.96

 Uniform

0.92

 Advantage

0.84

 equivalent

0.84

 Logo

0.81

Â®

0.80

 Certified

0.79

 equivalents

0.79

 terminology

0.75

 trademark

0.74

Activations Density 0.892%

technical terms and acronyms related to technology and industry

references to government or technical entities, standards, or equipment

No Comments

No Known Activations