INDEX

Explanations

No Explanations Found

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Payton

-0.70

 pizz

-0.66

 Falcons

-0.66

Bridge

-0.62

 Savior

-0.62

 Scarborough

-0.61

 Hispan

-0.61

 pont

-0.61

 Lans

-0.58

 pinpoint

-0.58

POSITIVE LOGITS

quickShipAvailable

1.05

oult

0.81

soDeliveryDate

0.75

arity

0.72

ILY

0.72

isSpecialOrderable

0.70

ngth

0.67

agents

0.66

advertising

0.66

intage

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.