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

PLIED

-0.86

phe

-0.80

iquid

-0.78

ascript

-0.78

 EDITION

-0.78

Pwr

-0.74

ription

-0.72

 AUTH

-0.71

romeda

-0.70

nery

-0.70

POSITIVE LOGITS

 Blocks

0.66

 Strait

0.65

eworthy

0.64

 Signs

0.64

 Recession

0.62

 Mold

0.62

 Cups

0.62

 Rules

0.61

Happy

0.61

 Territories

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.