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

emort

-0.86

actionDate

-0.77

arist

-0.73

 Plaintiff

-0.68

 guiIcon

-0.67

 Aerospace

-0.66

phasis

-0.66

 Patriot

-0.66

 anticipation

-0.65

SpaceEngineers

-0.65

POSITIVE LOGITS

nell

0.94

entimes

0.80

 Canaver

0.77

bot

0.77

gow

0.75

 mouth

0.73

 nodd

0.72

Bot

0.69

mouth

0.68

 steril

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.