INDEX

Explanations

words related to criminal activities, specifically theft

oai_token-act-pair · gpt-3.5-turbo

terminology related to theft

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

 Reynolds

-0.76

 Zucker

-0.71

PRES

-0.65

 evaluates

-0.65

 tuned

-0.65

enegger

-0.65

hel

-0.63

etus

-0.63

ghan

-0.63

ben

-0.63

POSITIVE LOGITS

 theft

3.73

 thefts

2.91

 Theft

2.60

 thieves

2.47

 thief

2.26

 robbery

2.07

 stealing

2.02

 burglary

1.93

 vandalism

1.86

 stolen

1.85

Activations Density 0.018%

words related to criminal activities, specifically theft

terminology related to theft

No Comments

No Known Activations