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

 Paste

-0.73

 Champ

-0.71

Features

-0.68

Downloadha

-0.67

ught

-0.64

 Ended

-0.64

racuse

-0.64

 Throne

-0.64

edom

-0.63

 Normandy

-0.63

POSITIVE LOGITS

å¥³

0.76

ients

0.72

kus

0.69

YP

0.67

naires

0.66

å¸

0.65

eno

0.64

OHN

0.63

lining

0.63

OSE

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.