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

dom

-0.69

rav

-0.64

 preached

-0.63

 favoring

-0.63

 arisen

-0.62

tube

-0.61

 tube

-0.60

 propose

-0.60

 Sabha

-0.60

 repeal

-0.59

POSITIVE LOGITS

quickShipAvailable

0.99

0.72

 Mehran

0.69

livious

0.68

ihilation

0.67

Balt

0.66

maxwell

0.66

eni

0.66

clus

0.65

 Malf

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.