INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ly

-0.76

acc

-0.70

inventoryQuantity

-0.68

 Offer

-0.67

irin

-0.67

 loaf

-0.67

Daily

-0.66

itri

-0.64

il

-0.63

azo

-0.62

POSITIVE LOGITS

:[

0.67

mie

0.67

KH

0.67

outheast

0.67

untled

0.67

Fug

0.66

Ó

0.66

Enlarge

0.65

0.64

wcs

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.