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

inventoryQuantity

-0.71

erness

-0.71

 Ranked

-0.67

LOS

-0.67

Toronto

-0.66

const

-0.65

impact

-0.65

TOR

-0.65

Development

-0.65

lol

-0.64

POSITIVE LOGITS

ainer

0.71

 Zeit

0.66

entary

0.62

agen

0.62

 Ange

0.60

pherd

0.60

 Nadu

0.58

atic

0.56

assi

0.56

 convin

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.