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

ulin

-0.67

itia

-0.65

versely

-0.65

cum

-0.63

RPG

-0.62

alys

-0.62

MQ

-0.60

 commuting

-0.60

etting

-0.60

ensibly

-0.59

POSITIVE LOGITS

ï¸

0.71

arks

0.70

xus

0.68

]}

0.67

å£«

0.66

uts

0.63

)]

0.62

 dont

0.61

 Kenya

0.60

vre

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.