INDEX

Explanations

phrases related to terrorist plots and attacks

oai_token-act-pair · gpt-3.5-turbo

terms related to terrorism and terrorist activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

galitarian

-0.86

 Vest

-0.73

 Veter

-0.72

 Lunar

-0.72

utral

-0.69

UV

-0.68

orem

-0.68

ðĿ

-0.67

RAL

-0.67

mount

-0.66

POSITIVE LOGITS

 terror

1.09

 terrorism

1.03

 bombing

1.03

 terrorists

1.00

 terrorist

0.97

 Daesh

0.96

 jihad

0.95

 extremism

0.93

 extremists

0.93

 bombings

0.92

Activations Density 0.140%

phrases related to terrorist plots and attacks

terms related to terrorism and terrorist activities

No Comments

No Known Activations