INDEX

Explanations

names related to Russian officials

oai_token-act-pair · gpt-3.5-turbo

references to prominent Russian individuals, particularly politicians and diplomats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Pear

-0.94

 Cook

-0.79

 cider

-0.74

Pear

-0.72

 Camel

-0.70

TC

-0.70

 Baylor

-0.69

Whe

-0.69

 Palmer

-0.69

Fox

-0.68

POSITIVE LOGITS

 Sergei

2.88

 Dmitry

2.83

 Sergey

2.68

 Mikhail

2.51

 Dmit

2.37

 Igor

2.27

 Ukrainians

2.26

 Ukrainian

2.25

Putin

2.21

 Nikol

2.20

Activations Density 0.068%

names related to Russian officials

references to prominent Russian individuals, particularly politicians and diplomats

No Comments

No Known Activations