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

 wrong

-0.75

 Tsukuyomi

-0.74

 blackout

-0.72

Nin

-0.71

 Bunker

-0.66

 sunset

-0.64

 Seah

-0.64

 incorrect

-0.63

 surpr

-0.62

POSITIVE LOGITS

acco

0.76

phia

0.72

zag

0.72

mbuds

0.70

oug

0.68

ruit

0.66

itsch

0.66

geon

0.64

azar

0.64

uce

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.