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

 Nort

-0.69

 Argent

-0.68

ETF

-0.66

 Ogre

-0.65

 Compass

-0.65

 Seah

-0.65

 shirt

-0.64

 Dome

-0.64

 Belt

-0.62

 Pant

-0.62

POSITIVE LOGITS

issance

0.76

BOOK

0.76

 slam

0.74

Bee

0.74

sonian

0.72

ydia

0.72

çĶ°

0.72

ickets

0.71

userc

0.71

inventoryQuantity

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.