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

Missing

-0.76

Traditional

-0.73

balance

-0.72

significant

-0.71

flush

-0.71

packed

-0.71

set

-0.68

ilton

-0.68

otle

-0.67

ented

-0.67

POSITIVE LOGITS

 Archdemon

0.73

raviolet

0.73

 alley

0.72

 tunnels

0.72

NetMessage

0.71

 enlarg

0.71

 corridors

0.70

vow

0.68

 labs

0.67

 shaft

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.