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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 contrace

-0.74

iles

-0.68

artisan

-0.66

 arrang

-0.66

legged

-0.62

 parenting

-0.62

worthy

-0.62

ties

-0.62

ilon

-0.62

 Jasper

-0.61

POSITIVE LOGITS

[*]

0.77

-|

0.72

 Moder

0.66

 Cool

0.65

 tanker

0.65

assetsadobe

0.64

apan

0.64

ampions

0.64

>[

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.