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

IFT

-0.77

Jet

-0.77

hens

-0.74

Spread

-0.73

peed

-0.72

hing

-0.71

bourne

-0.70

auri

-0.69

bral

-0.67

externalActionCode

-0.66

POSITIVE LOGITS

 total

1.52

total

1.27

 TOTAL

1.20

 Total

1.05

OTAL

0.81

Total

0.77

 totals

0.67

tac

0.66

 Slave

0.65

 totality

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.