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

IPM

-0.86

îĢ

-0.78

SPONSORED

-0.78

 Cheng

-0.73

INTON

-0.70

VB

-0.70

 disadvant

-0.69

 adultery

-0.65

anship

-0.65

 Kendall

-0.65

POSITIVE LOGITS

uta

0.82

udo

0.80

rets

0.77

uct

0.76

iments

0.76

 commissions

0.75

uckland

0.74

enf

0.73

amental

0.72

ning

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.