INDEX

Explanations

situations involving conflict or legal actions

oai_token-act-pair · gpt-3.5-turbo

mentions of authority figures or institutions related to crime and misconduct

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 ILCS

-0.94

soDeliveryDate

-0.77

":"/

-0.75

DragonMagazine

-0.73

 Anyway

-0.73

 ideally

-0.72

 preferably

-0.69

ebook

-0.67

Anyway

-0.67

 depends

-0.66

POSITIVE LOGITS

 mistakenly

1.23

 failed

1.14

 refused

1.10

 accidentally

1.07

 breached

1.06

 unexpectedly

1.04

 interfered

1.02

 clashed

1.00

 complained

0.99

 botched

0.94

Activations Density 0.239%

situations involving conflict or legal actions

mentions of authority figures or institutions related to crime and misconduct

No Comments

No Known Activations