INDEX

Explanations

proper nouns, specifically focusing on names such as "Stephen" with varying degrees of importance or infamy

oai_token-act-pair · gpt-3.5-turbo

references to individuals named Stephen

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

eer

-1.06

footed

-0.77

 circ

-0.74

engers

-0.73

igi

-0.72

LOAD

-0.71

 guiActiveUnfocused

-0.69

mented

-0.67

fet

-0.66

exempt

-0.65

POSITIVE LOGITS

 Hawking

1.28

 Paddock

1.08

 Colbert

0.99

son

0.89

ology

0.88

Fry

0.87

ases

0.85

 Strange

0.83

 Stras

0.83

 Harper

0.82

Activations Density 0.016%

proper nouns, specifically focusing on names such as "Stephen" with varying degrees of importance or infamy

references to individuals named Stephen

No Comments

No Known Activations