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

Reviewed

-0.69

 disinfect

-0.69

 steril

-0.68

 psychiat

-0.64

 Austral

-0.64

ologne

-0.62

 Alter

-0.62

 Disabled

-0.61

ardless

-0.61

YL

-0.61

POSITIVE LOGITS

Points

0.75

icky

0.70

acho

0.70

¤

0.70

ances

0.69

algia

0.68

acca

0.67

atin

0.65

ÃŃ

0.65

Boss

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.