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

axis

-0.79

sid

-0.74

JD

-0.73

abulary

-0.73

runners

-0.72

uate

-0.69

 Wilde

-0.68

runner

-0.66

laus

-0.66

igma

-0.65

POSITIVE LOGITS

 Archdemon

0.81

éĹĺ

0.78

¥µ

0.73

ãĤ¯

0.73

ItemTracker

0.72

ĪĴ

0.72

 Bolshevik

0.69

 Tradable

0.68

 Loch

0.67

 Chatt

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.