INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Devices

-0.78

shapeshifter

-0.67

 Printing

-0.66

 Disorders

-0.65

 Images

-0.63

 Synd

-0.63

 Decre

-0.62

 Machines

-0.61

 Savings

-0.61

 Junk

-0.60

POSITIVE LOGITS

dn

0.68

plet

0.65

 showc

0.64

rera

0.64

SCP

0.63

owler

0.62

kell

0.62

steen

0.61

git

0.61

sol

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.