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

Dist

-0.68

acs

-0.68

ortium

-0.67

USA

-0.66

REF

-0.66

Ret

-0.66

Keith

-0.65

-0.64

dor

-0.64

ģĸ

-0.64

POSITIVE LOGITS

 Baal

0.64

Zan

0.64

Zam

0.62

 Quan

0.62

gha

0.62

 Indra

0.61

Za

0.60

iken

0.60

 Tian

0.59

 terms

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.