INDEX

Explanations

references to customization or unique tailored products

oai_token-act-pair · gpt-3.5-turbo

terms related to custom-made products or features

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

ï¸

-0.84

 CrossRef

-0.77

loo

-0.75

Æ

-0.74

 Kinn

-0.73

 Lauder

-0.73

udi

-0.71

trump

-0.71

wick

-0.71

Mub

-0.70

POSITIVE LOGITS

isable

1.54

izations

1.43

isations

1.25

ised

1.24

arily

1.22

izable

1.21

isation

1.12

 tailored

0.99

ization

0.99

izing

0.91

Activations Density 0.018%

references to customization or unique tailored products

terms related to custom-made products or features

No Comments

No Known Activations