INDEX

Explanations

comparisons using the word "like"

oai_token-act-pair · gpt-3.5-turbo

comparisons or analogies using the word "like."

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

utenberg

-0.76

aptic

-0.75

xious

-0.68

ulty

-0.65

idable

-0.65

inas

-0.64

arious

-0.63

ueless

-0.63

 underestimated

-0.62

elin

-0.62

POSITIVE LOGITS

lihood

1.44

 ours

1.36

liest

1.18

 yours

1.10

lier

1.10

 theirs

1.10

 hers

1.05

 minded

0.85

minded

0.84

liness

0.75

Activations Density 0.065%

comparisons using the word "like"

comparisons or analogies using the word "like."

No Comments

No Known Activations