INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Arts

-0.68

tnc

-0.68

 Assessment

-0.63

 urge

-0.63

 assailants

-0.61

 resilience

-0.60

 proceed

-0.60

DragonMagazine

-0.60

 Refuge

-0.60

 Sail

-0.59

POSITIVE LOGITS

byter

0.81

 Chocobo

0.79

vier

0.78

exempt

0.73

mast

0.73

stock

0.72

patch

0.70

Dub

0.69

gets

0.69

christ

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.