INDEX

Explanations

phrases related to countries experiencing instability or turmoil

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate political instability and turmoil

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

 Precision

-0.73

 availability

-0.70

 suggestion

-0.69

 frequencies

-0.68

 quotation

-0.67

 frequency

-0.66

 quotes

-0.64

 chats

-0.62

 Frequency

-0.62

 Detect

-0.61

POSITIVE LOGITS

 economically

1.34

 territ

1.02

 diplom

0.97

 politically

0.95

 milit

0.95

 financially

0.94

 ideologically

0.88

 technologically

0.84

 culturally

0.83

 spiritually

0.83

Activations Density 0.472%

phrases related to countries experiencing instability or turmoil

phrases that indicate political instability and turmoil

No Comments

No Known Activations