INDEX

Explanations

references to suspects in criminal investigations

oai_token-act-pair · gpt-3.5-turbo

mentions of suspects in a crime-related context

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

galitarian

-0.73

atism

-0.72

 stead

-0.70

 Remastered

-0.69

abeth

-0.67

psey

-0.66

atters

-0.66

Morning

-0.65

issance

-0.64

 Hear

-0.63

POSITIVE LOGITS

 suspects

0.82

 suspect

0.76

itives

0.70

 arson

0.68

ively

0.66

 perpetrator

0.65

fully

0.65

 Guilty

0.65

 gunman

0.64

hunt

0.64

Activations Density 0.022%

references to suspects in criminal investigations

mentions of suspects in a crime-related context

No Comments

No Known Activations