INDEX

Explanations

words related to specific fields or domains, such as infant care, digital technology, public matters, road races, database management, public health, legal or financial sectors, virtual reality, family law, retail, metric systems, and others

oai_token-act-pair · gpt-3.5-turbo

terms related to societal structures and systems

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Yorkers

-0.78

paio

-0.69

olicited

-0.68

inx

-0.66

orsi

-0.64

atism

-0.64

oy

-0.61

Americans

-0.59

Tags

-0.59

apego

-0.58

POSITIVE LOGITS

 vicinity

1.29

 realm

1.14

 context

1.09

 arena

1.05

 midst

1.02

 guise

0.99

 area

0.98

 aisle

0.97

 attic

0.97

ixties

0.96

Activations Density 0.663%

words related to specific fields or domains, such as infant care, digital technology, public matters, road races, database management, public health, legal or financial sectors, virtual reality, family law, retail, metric systems, and others

terms related to societal structures and systems

No Known Activations

words related to specific fields or domains, such as infant care, digital technology, public matters, road races, database management, public health, legal or financial sectors, virtual reality, family law, retail, metric systems, and others

terms related to societal structures and systems

No Known Activations