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

anamo

-0.72

due

-0.72

 mosqu

-0.66

viol

-0.65

press

-0.64

pill

-0.63

 horm

-0.63

weather

-0.63

pee

-0.62

frames

-0.62

POSITIVE LOGITS

azor

0.76

ka

0.68

tical

0.67

 Nether

0.64

 Emirates

0.64

 Switzerland

0.62

 Tanzania

0.62

 Kinnikuman

0.62

)=(

0.61

 sclerosis

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.