INDEX

Explanations

phrases or sentences indicating the conclusion or end of something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating endings or closures of situations 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

vich

-0.78

 Adin

-0.69

listed

-0.65

estate

-0.63

oir

-0.63

ilk

-0.60

iolet

-0.60

hower

-0.59

 Licensed

-0.59

iar

-0.59

POSITIVE LOGITS

 halt

1.27

 conclusion

1.19

 climax

1.08

 scree

1.02

 abrupt

1.02

 culmination

0.96

 fruition

0.93

end

0.92

 stop

0.88

 realization

0.86

Activations Density 0.054%

phrases or sentences indicating the conclusion or end of something

phrases indicating endings or closures of situations or experiences

No Comments

No Known Activations