INDEX

Explanations

phrases related to law enforcement or police activity, especially focusing on off-duty scenarios

oai_token-act-pair · gpt-3.5-turbo

references to police officers on duty or off-duty contexts

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

 Juliet

-0.84

 Rosenthal

-0.76

hematic

-0.74

anz

-0.74

 Tate

-0.73

vae

-0.72

ergy

-0.71

iques

-0.68

TED

-0.67

 Ridley

-0.66

POSITIVE LOGITS

 Duty

1.16

duty

1.13

uty

1.01

 duty

0.99

naire

0.73

hov

0.72

 obligation

0.71

ftime

0.71

 solicitation

0.70

enei

0.69

Activations Density 0.009%

phrases related to law enforcement or police activity, especially focusing on off-duty scenarios

references to police officers on duty or off-duty contexts

No Comments

No Known Activations