INDEX

Explanations

phrases indicating physical force or confinement

oai_token-act-pair · gpt-3.5-turbo

descriptions of physical confrontations or violent interactions

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

 Affect

-0.70

invoke

-0.68

DragonMagazine

-0.65

inations

-0.65

lance

-0.65

imei

-0.65

akings

-0.63

MQ

-0.63

hess

-0.62

xual

-0.61

POSITIVE LOGITS

 bushes

1.36

 walls

1.27

 cliffs

1.19

 ropes

1.11

 rocks

1.09

 fences

1.07

 stairs

1.07

 scaff

1.07

 shelves

1.07

 trees

1.06

Activations Density 0.208%

phrases indicating physical force or confinement

descriptions of physical confrontations or violent interactions

No Comments

No Known Activations