INDEX

Explanations

mentions of military or law enforcement deployment

oai_token-act-pair · gpt-3.5-turbo

the term "deployed" in various contexts related to military or operational forces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

âĶĢâĶĢ

-0.73

jar

-0.71

iasis

-0.70

lic

-0.68

deal

-0.67

she

-0.66

nings

-0.66

otten

-0.65

estamp

-0.64

bm

-0.63

POSITIVE LOGITS

ilitary

1.10

 stationed

0.89

 troops

0.88

 abroad

0.82

 patrols

0.81

illin

0.78

 deployed

0.77

aeda

0.74

 marines

0.73

 warships

0.73

Activations Density 0.044%

mentions of military or law enforcement deployment

the term "deployed" in various contexts related to military or operational forces

No Comments

No Known Activations