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

acers

-0.71

 STATES

-0.69

 Leopard

-0.67

oppy

-0.64

enegger

-0.64

arma

-0.64

atto

-0.64

ems

-0.64

 Welsh

-0.63

 Roses

-0.63

POSITIVE LOGITS

asia

0.72

frame

0.68

way

0.65

omaly

0.61

======

0.60

wed

0.60

 Anchorage

0.59

 pageant

0.58

 expedition

0.57

trust

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.