INDEX

Explanations

terms related to a "package" or specified set of items or conditions

oai_token-act-pair · gpt-3.5-turbo

references to "package" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

nesota

-0.80

ffe

-0.73

shire

-0.73

avin

-0.72

aft

-0.71

icial

-0.68

 Draper

-0.68

alties

-0.66

had

-0.66

 Colleg

-0.66

POSITIVE LOGITS

 packages

0.98

 package

0.92

 Package

0.83

packages

0.82

 bundle

0.73

 packaging

0.72

 manifests

0.72

 shipments

0.70

eers

0.69

boxes

0.68

Activations Density 0.010%

terms related to a "package" or specified set of items or conditions

references to "package" in various contexts

No Comments

No Known Activations