INDEX

Explanations

phrases related to criminal activities or charges

oai_token-act-pair · gpt-3.5-turbo

terms related to criminal activity and offenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Whe

-0.84

 Ratio

-0.81

 ratio

-0.77

 ratios

-0.73

idges

-0.72

Reviewed

-0.71

Temperature

-0.69

 warmed

-0.68

Opt

-0.68

oration

-0.67

POSITIVE LOGITS

 criminal

3.57

criminal

3.11

 Criminal

2.49

riminal

2.21

 criminality

2.07

 criminals

2.00

 felony

1.85

 crime

1.84

 criminally

1.82

 Crimes

1.75

Activations Density 0.028%

phrases related to criminal activities or charges

terms related to criminal activity and offenses

No Comments

No Known Activations