INDEX

Explanations

instances of physical violence

oai_token-act-pair · gpt-3.5-turbo

references to violence and physical confrontations involving individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ItemImage

-0.75

ITNESS

-0.69

iterranean

-0.66

 Cosponsors

-0.64

foreseen

-0.64

BIL

-0.64

ItemThumbnailImage

-0.63

å¼

-0.63

paid

-0.63

POSITIVE LOGITS

 away

1.05

 down

0.94

out

0.92

 senseless

0.90

 tires

0.89

awa

0.87

 unconscious

0.86

 loose

0.86

 into

0.85

nuts

0.84

Activations Density 0.246%

instances of physical violence

references to violence and physical confrontations involving individuals

No Comments

No Known Activations