INDEX

Explanations

proper nouns related to individuals from various fields like sports, entertainment, and politics

oai_token-act-pair · gpt-3.5-turbo

names of notable individuals and organizations

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

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

soever

-0.71

upon

-0.63

Synopsis

-0.63

BuyableInstoreAndOnline

-0.62

Thumbnail

-0.59

levard

-0.57

 newcom

-0.55

itant

-0.54

ocate

-0.54

ijah

-0.54

POSITIVE LOGITS

 wasn

0.98

 existed

0.97

isn

0.94

 exists

0.94

 belonged

0.93

 hadn

0.93

 belongs

0.92

 lacks

0.91

 hasn

0.89

 differently

0.88

Activations Density 0.647%

proper nouns related to individuals from various fields like sports, entertainment, and politics

names of notable individuals and organizations

No Comments

No Known Activations