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

ayne

-0.80

sie

-0.74

icut

-0.73

abet

-0.72

stab

-0.72

oglu

-0.70

ril

-0.68

addons

-0.66

wic

-0.66

immer

-0.66

POSITIVE LOGITS

mma

0.67

 Carnage

0.67

Interstitial

0.65

 Supporters

0.63

GROUND

0.63

 enhances

0.62

 Dinosaur

0.61

 shoots

0.61

estamp

0.60

 Revolution

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.