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

-0.70

Â·

-0.69

-0.68

unt

-0.66

âķĲ

-0.66

cellence

-0.66

ä¸Ĭ

-0.64

tesy

-0.64

Footnote

-0.63

Ã©t

-0.63

POSITIVE LOGITS

Klu

0.66

 isEnabled

0.66

 panels

0.63

 methods

0.62

 Moor

0.62

Lys

0.62

 mobs

0.62

Sov

0.62

 sailors

0.62

 factories

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.