INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

quartered

-0.77

tein

-0.71

otton

-0.68

oustic

-0.68

©¶æ

-0.67

avascript

-0.65

 destro

-0.65

velength

-0.63

 resin

-0.63

 pores

-0.63

POSITIVE LOGITS

too

1.56

Too

1.14

too

1.08

Too

0.99

visors

0.73

 needless

0.72

aries

0.71

Fight

0.70

ories

0.67

 Steph

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.