INDEX

Explanations

terms related to the Department of Homeland Security

oai_token-act-pair · gpt-3.5-turbo

references to the Department of Homeland Security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 unsub

-0.73

ISTER

-0.73

ä»£

-0.71

-0.65

 pend

-0.63

 menstrual

-0.62

 deaf

-0.62

orem

-0.62

ivia

-0.61

 subscribed

-0.60

POSITIVE LOGITS

 Security

1.01

security

0.90

istan

0.88

 Defense

0.88

 Patrol

0.86

 security

0.86

 Homeland

0.84

 Guard

0.81

 Terror

0.81

 Guards

0.80

Activations Density 0.012%

terms related to the Department of Homeland Security

references to the Department of Homeland Security

No Comments

No Known Activations