INDEX

Explanations

phrases related to violent actions or incidents

oai_token-act-pair · gpt-3.5-turbo

terms associated with violent and excessive actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 slightest

-0.75

66666666

-0.69

croft

-0.66

ĪĴ

-0.66

faith

-0.65

aves

-0.64

 Patriarch

-0.62

parts

-0.61

otes

-0.61

angers

-0.59

POSITIVE LOGITS

 spree

1.53

 rampage

1.01

ãĥ¼ãĤ¯

0.84

="/

0.79

 looting

0.77

 Hebdo

0.73

ãĥ¢

0.72

ãĥ¥

0.71

steen

0.70

 Mania

0.67

Activations Density 0.009%

phrases related to violent actions or incidents

terms associated with violent and excessive actions

No Comments

No Known Activations