INDEX

Explanations

phrases related to violent attacks and terrorism

oai_token-act-pair · gpt-3.5-turbo

phrases related to attacks and violence

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

ãĤ´ãĥ³

-0.86

igmat

-0.83

dra

-0.82

ãĤ¦ãĤ¹

-0.81

catentry

-0.80

ripp

-0.78

ById

-0.77

ilk

-0.77

lost

-0.74

omaly

-0.70

POSITIVE LOGITS

 civilians

1.18

 embassies

1.17

 pedestrians

1.11

 innocent

1.09

 policemen

1.08

 journalists

1.05

 buses

1.03

 unarmed

1.02

 churches

1.01

 mosques

0.99

Activations Density 0.197%

phrases related to violent attacks and terrorism

phrases related to attacks and violence

No Comments

No Known Activations