INDEX

Explanations

references to physical packages or deliveries

oai_token-act-pair · gpt-3.5-turbo

references to "package"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nesota

-0.86

bered

-0.77

alties

-0.74

aft

-0.70

baugh

-0.69

shire

-0.69

bes

-0.67

osate

-0.66

farious

-0.64

sm

-0.64

POSITIVE LOGITS

 packages

0.85

packages

0.83

 Package

0.76

 Contents

0.74

 package

0.74

aging

0.70

nam

0.69

 manifests

0.68

 Includes

0.67

 peanuts

0.66

Activations Density 0.017%

references to physical packages or deliveries

references to "package"

No Comments

No Known Activations