INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

astically

-0.96

GES

-0.80

pter

-0.80

UNCH

-0.70

ayer

-0.69

roots

-0.68

uct

-0.68

 Unsure

-0.67

zeb

-0.66

GE

-0.65

POSITIVE LOGITS

 spoil

0.66

 Romero

0.66

mone

0.65

 Lowe

0.62

alde

0.61

etc

0.60

yrinth

0.60

 Fernandez

0.59

anian

0.59

 Giov

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.