INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ascus

-0.86

uria

-0.82

brance

-0.79

Benz

-0.78

 menstru

-0.73

zai

-0.73

netflix

-0.70

liga

-0.70

urden

-0.69

eday

-0.68

POSITIVE LOGITS

[|

0.73

 Sect

0.67

¦

0.65

bold

0.63

 Unle

0.62

 Cooking

0.60

CRA

0.60

gre

0.60

 Smooth

0.60

 Inquiry

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.