INDEX

Explanations

phrases related to legal and criminal activities involving a specific individual named "Nchito."

oai_token-act-pair · gpt-3.5-turbo

the repetition of specific names and terms related to individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

comed

-0.78

TPPStreamerBot

-0.74

bleacher

-0.71

¥ŀ

-0.70

 cryst

-0.68

ß

-0.67

OWS

-0.67

mable

-0.67

hover

-0.67

Þ

-0.65

POSITIVE LOGITS

ito

1.25

zzi

1.01

zza

0.94

udo

0.92

uto

0.86

 Marcos

0.80

osa

0.80

cha

0.80

apan

0.80

 Ortiz

0.79

Activations Density 0.010%

phrases related to legal and criminal activities involving a specific individual named "Nchito."

the repetition of specific names and terms related to individuals or entities

No Comments

No Known Activations