INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

DAQ

-0.79

merce

-0.68

Merit

-0.67

Demand

-0.66

 conduc

-0.63

 ethos

-0.63

DT

-0.61

 challeng

-0.61

 ACTIONS

-0.61

 endeavour

-0.61

POSITIVE LOGITS

 married

1.57

 Married

1.25

married

1.07

BuyableInstoreAndOnline

0.77

uana

0.76

 Painter

0.73

 ILCS

0.71

abeth

0.67

onian

0.65

 murderer

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.