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

itia

-0.72

 Kell

-0.71

 Williamson

-0.70

fulness

-0.69

oleon

-0.67

 Cater

-0.67

ournal

-0.65

 Hobby

-0.64

Yel

-0.64

 Grill

-0.63

POSITIVE LOGITS

raq

0.74

inventoryQuantity

0.73

catentry

0.68

nel

0.67

artifacts

0.66

cffffcc

0.66

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.64

deb

0.63

future

0.63

 glim

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.