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

 Niet

-0.75

 Towns

-0.74

 Phelps

-0.71

 Nanto

-0.71

 Tycoon

-0.70

 Bows

-0.66

-0.65

 Sung

-0.65

Rin

-0.62

 Amend

-0.61

POSITIVE LOGITS

 partName

0.78

amb

0.70

kil

0.69

Ã©r

0.68

åī

0.67

ority

0.67

odynam

0.66

usercontent

0.66

iterranean

0.64

oat

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.