INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

=\"

-0.83

 Simulator

-0.67

\"

-0.65

nil

-0.65

 annotations

-0.63

 theoret

-0.62

SourceFile

-0.62

 manifests

-0.60

anooga

-0.60

 resc

-0.59

POSITIVE LOGITS

itz

2.01

heid

0.73

azz

0.71

iz

0.70

itten

0.70

aim

0.69

odge

0.69

 Warm

0.69

Air

0.68

abo

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.