INDEX

Explanations

references to the United States military

oai_token-act-pair · gpt-3.5-turbo

references to the United States or its military involvement

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

 partName

-0.84

*/(

-0.73

bred

-0.72

 srfAttach

-0.70

 "$:/

-0.68

MpServer

-0.68

sections

-0.67

 Newton

-0.67

Ont

-0.67

£ı

-0.66

POSITIVE LOGITS

 Embassy

0.95

 embassy

0.95

 diplomats

0.93

 airstrikes

0.93

 spies

0.88

 troop

0.88

 diplomatic

0.87

 counterterrorism

0.86

 neocons

0.86

 Ambassador

0.85

Activations Density 0.176%

references to the United States military

references to the United States or its military involvement

No Comments

No Known Activations