INDEX

Explanations

mentions of terrorist-related terms and activities

oai_token-act-pair · gpt-3.5-turbo

references to terrorists and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

shire

-0.76

ership

-0.72

 Taste

-0.69

irth

-0.68

Wo

-0.66

vent

-0.65

 Wine

-0.65

NRS

-0.65

PT

-0.65

itor

-0.64

POSITIVE LOGITS

 terrorists

1.27

 terrorist

1.02

 bombers

0.97

terrorist

0.95

 mastermind

0.95

 gunmen

0.92

 attackers

0.91

ãĥ³ãĤ¸

0.87

apons

0.87

 murderers

0.85

Activations Density 0.008%

mentions of terrorist-related terms and activities

references to terrorists and related terminology

No Comments

No Known Activations