INDEX

Explanations

pronouns and possessive pronouns used in conjunction with descriptors or relationships

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns indicating personal attributes or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

nesty

-0.83

ĳå£«

-0.82

wrap

-0.78

asus

-0.75

atel

-0.74

haus

-0.73

ominated

-0.73

apo

-0.73

Ban

-0.72

pty

-0.72

POSITIVE LOGITS

 emotions

1.51

 surroundings

1.51

 perceptions

1.49

 instincts

1.46

 desires

1.42

 passions

1.40

own

1.39

 beliefs

1.39

 feelings

1.38

 psyche

1.38

Activations Density 0.264%

pronouns and possessive pronouns used in conjunction with descriptors or relationships

possessive pronouns indicating personal attributes or experiences

No Comments

No Known Activations