INDEX

Explanations

descriptions or attributes related to the spatial concept of "outer."

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "outer" or "outer layers."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

eva

-0.73

ILLE

-0.72

ute

-0.72

 Guilty

-0.70

USE

-0.69

BILITY

-0.68

inatory

-0.67

yrs

-0.66

awaru

-0.66

NPR

-0.65

POSITIVE LOGITS

 outer

1.06

most

0.96

 Outer

0.95

wear

0.94

borough

0.86

 casing

0.84

outer

0.84

 garments

0.82

neath

0.81

 perimeter

0.80

Activations Density 0.003%

descriptions or attributes related to the spatial concept of "outer."

references to the concept of "outer" or "outer layers."

No Comments

No Known Activations