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

enegger

-0.73

 mole

-0.73

 termin

-0.68

ierre

-0.67

 Spur

-0.66

 Turing

-0.65

 Canaver

-0.64

 horizont

-0.64

 supp

-0.63

 Lieutenant

-0.63

POSITIVE LOGITS

#$

0.82

rencies

0.78

mage

0.77

heon

0.76

clock

0.75

amped

0.73

USS

0.72

Va

0.71

igm

0.71

dozen

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.