INDEX

Explanations

mentions of the activity of surfing

oai_token-act-pair · gpt-3.5-turbo

mentions of surfing and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Reloaded

-0.66

NESS

-0.65

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.65

FORE

-0.65

 Lyons

-0.64

Detailed

-0.63

 Cain

-0.63

uments

-0.63

 menstrual

-0.62

chy

-0.62

POSITIVE LOGITS

 surfing

1.02

boards

0.97

 Surf

0.92

acing

0.92

 surf

0.89

acers

0.87

boarding

0.85

yip

0.82

 Beach

0.81

icial

0.80

Activations Density 0.006%

mentions of the activity of surfing

mentions of surfing and related activities

No Comments

No Known Activations