INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 countdown

-0.68

Â±

-0.63

 noon

-0.62

 KING

-0.62

itz

-0.58

 Barney

-0.58

Ãī

-0.58

antasy

-0.57

 realization

-0.56

POSITIVE LOGITS

omaly

0.78

otin

0.77

unin

0.73

alian

0.70

osate

0.69

ocrat

0.68

jen

0.68

assic

0.67

lyak

0.67

DoS

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.