INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

berra

-0.56

 âĢº

-0.55

uminati

-0.54

 Archdemon

-0.53

Interested

-0.52

 Paran

-0.50

 attm

-0.49

 Flavoring

-0.49

 Slayer

-0.49

taboola

-0.48

POSITIVE LOGITS

kson

0.63

espie

0.62

 recalled

0.59

 laughed

0.55

 vetoed

0.54

enson

0.53

yden

0.51

 wrote

0.51

 conceded

0.51

 detractors

0.51

Activations Density 0.417%

names of individuals

proper nouns, specifically names of people

No Comments

No Known Activations