INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ETH

-0.89

OTHER

-0.79

ATURES

-0.79

soDeliveryDate

-0.79

UID

-0.74

ACTED

-0.73

GREEN

-0.73

Farm

-0.72

Hart

-0.72

GAME

-0.72

POSITIVE LOGITS

 resists

0.82

 promotions

0.72

 defied

0.70

 dates

0.69

 favour

0.69

enegger

0.68

 immune

0.68

 frust

0.68

 preferred

0.67

ategories

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.