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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cffffcc

-0.78

displayText

-0.74

ney

-0.71

 Entered

-0.69

neys

-0.67

 EntityItem

-0.63

catentry

-0.62

robat

-0.62

 lect

-0.62

rence

-0.61

POSITIVE LOGITS

ity

0.74

izable

0.68

photos

0.66

andra

0.66

ingo

0.65

ists

0.62

IVE

0.62

Smy

0.61

ONE

0.61

 Tara

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.