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

ItemImage

-0.81

cent

-0.73

canon

-0.72

bur

-0.66

seek

-0.65

awa

-0.65

Det

-0.63

istant

-0.63

taboola

-0.62

oral

-0.61

POSITIVE LOGITS

ãĤ¦ãĤ¹

0.72

 Briggs

0.71

 champagne

0.70

sted

0.66

emale

0.65

 Fior

0.64

esters

0.64

ãĥ¼ãĥĨãĤ£

0.64

 Holland

0.63

irez

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.