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

ems

-0.72

 downgrade

-0.68

aber

-0.68

iour

-0.68

iggurat

-0.67

 bounded

-0.66

tho

-0.64

ades

-0.63

 overpowered

-0.62

emic

-0.62

POSITIVE LOGITS

AFTA

0.75

å£

0.66

spawn

0.64

estern

0.63

meat

0.63

gart

0.63

 Veterinary

0.62

Au

0.61

ãģĤ

0.61

vasive

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.