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

oidal

-0.79

 sidx

-0.75

ãĤ¯

-0.75

Org

-0.72

itol

-0.72

 Loft

-0.70

ðĿ

-0.70

ctive

-0.70

olesterol

-0.68

ÙĦ

-0.67

POSITIVE LOGITS

 privilege

0.68

 Honour

0.67

ometimes

0.65

teen

0.65

uncture

0.64

 guilt

0.64

 stricken

0.64

wana

0.64

 humour

0.63

earchers

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.