INDEX

Explanations

instances where someone is pretending or falsifying something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "pretend" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

KO

-0.69

 Lith

-0.66

 impacting

-0.63

iang

-0.63

UC

-0.63

oly

-0.62

 âĨĳ

-0.62

 Overall

-0.62

 Region

-0.62

 Tank

-0.61

POSITIVE LOGITS

 pretend

3.46

 pretended

2.66

 pretending

2.59

 disguise

1.54

 pret

1.47

pret

1.37

 Pret

1.36

 disgu

1.30

 phony

1.26

 fictitious

1.25

Activations Density 0.022%

instances where someone is pretending or falsifying something

instances of the word "pretend" and its variations

No Comments

No Known Activations