INDEX

Explanations

phrases indicating ongoing or remaining situations

oai_token-act-pair · gpt-3.5-turbo

phrases related to continuity or persistence

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

ramid

-0.81

DragonMagazine

-0.74

gage

-0.69

PsyNetMessage

-0.66

idth

-0.65

ongyang

-0.63

ellar

-0.63

esity

-0.62

isson

-0.61

 TOUR

-0.61

POSITIVE LOGITS

 unchanged

1.38

 untouched

1.24

 intact

1.22

 unanswered

1.15

 unresolved

1.13

 unsolved

1.13

 steadfast

1.12

 elusive

1.12

 unaffected

1.08

 unclear

1.08

Activations Density 0.042%

phrases indicating ongoing or remaining situations

phrases related to continuity or persistence

No Comments

No Known Activations