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

çīĪ

-0.71

 Brands

-0.67

 Patron

-0.66

 tatt

-0.64

èª

-0.64

folio

-0.64

 Papa

-0.63

ãĥĦ

-0.63

atche

-0.63

CoC

-0.63

POSITIVE LOGITS

ente

0.64

sed

0.64

uez

0.63

oris

0.62

rial

0.62

 nitrogen

0.61

ymes

0.59

 centr

0.57

ipher

0.57

elia

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.