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

icho

-0.81

ecause

-0.76

amily

-0.75

ãĢį

-0.72

ividual

-0.72

ogie

-0.71

lease

-0.68

aki

-0.68

ollow

-0.67

ikan

-0.67

POSITIVE LOGITS

 Mechdragon

0.76

 Scenes

0.71

 ASIC

0.60

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.60

 Soph

0.60

 Scarlett

0.59

senal

0.59

externalActionCode

0.58

 shares

0.57

 Chance

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.