INDEX

Explanations

references to arrests and arrest warrants

oai_token-act-pair · gpt-3.5-turbo

references to arrests and legal actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ÃŁ

-0.71

^^^^

-0.71

 snipp

-0.66

abbit

-0.64

 dressing

-0.62

Â¯Â¯Â¯Â¯

-0.58

ertility

-0.57

 embr

-0.57

 deceive

-0.56

burn

-0.56

POSITIVE LOGITS

 warrant

1.31

 warrants

1.28

ees

1.23

 Warrant

1.20

 affidavit

1.00

ee

0.98

rained

0.90

able

0.89

ments

0.88

 arrest

0.87

Activations Density 0.063%

references to arrests and arrest warrants

references to arrests and legal actions

No Comments

No Known Activations