INDEX

Explanations

descriptions of violent incidents, including shootings and robberies

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

references to individuals in a context involving violence or crime

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

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

ilogy

-0.88

pmwiki

-0.81

thumbnails

-0.78

odes

-0.76

endars

-0.76

enture

-0.74

ramid

-0.73

ights

-0.73

ibraries

-0.71

urrection

-0.71

POSITIVE LOGITS

 identified

1.19

 named

1.06

 Yose

1.04

 Edwin

1.04

 Mohamed

1.03

 Nguyen

1.01

 Gregory

1.00

 Vincent

1.00

 Timothy

0.99

 Harold

0.99

Activations Density 0.222%

descriptions of violent incidents, including shootings and robberies

references to individuals in a context involving violence or crime

No Comments

No Known Activations