INDEX

Explanations

words related to violent and criminal activities

oai_token-act-pair · gpt-3.5-turbo

terms related to homicide and extreme violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ellation

-0.83

ellar

-0.75

soType

-0.75

bits

-0.70

paren

-0.68

 misunder

-0.67

riched

-0.67

ivot

-0.67

BuyableInstoreAndOnline

-0.66

 indent

-0.66

POSITIVE LOGITS

 spree

1.14

 rampage

0.86

 perpetrated

0.85

 killings

0.83

 victims

0.78

ography

0.77

 inflicted

0.77

 murders

0.77

 Anonymous

0.77

 Victims

0.74

Activations Density 0.191%

words related to violent and criminal activities

terms related to homicide and extreme violence

No Comments

No Known Activations