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

 mathemat

-0.74

ledged

-0.70

 skelet

-0.68

 advoc

-0.68

 Palest

-0.67

laden

-0.65

 juven

-0.64

hog

-0.63

elled

-0.63

 lobe

-0.62

POSITIVE LOGITS

agne

0.65

example

0.65

 Franks

0.62

formance

0.62

 Certification

0.62

ĻĤ

0.61

itial

0.60

ven

0.60

"{

0.60

 Kickstarter

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.