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

aways

-0.77

Interstitial

-0.76

 Norn

-0.73

ouver

-0.71

thumbnails

-0.69

creen

-0.67

grain

-0.67

 Berm

-0.67

 Slaughter

-0.65

 actresses

-0.64

POSITIVE LOGITS

haps

0.69

azor

0.66

enza

0.65

eton

0.64

atively

0.60

CE

0.59

 Eagle

0.58

 flank

0.58

 bloc

0.57

 affili

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.