INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

encia

-0.74

enses

-0.72

 Sparks

-0.67

 Images

-0.66

 Gree

-0.64

nces

-0.63

 Credits

-0.63

RG

-0.62

 Photographer

-0.62

cens

-0.62

POSITIVE LOGITS

¼

0.86

foundation

0.69

 hind

0.67

 allev

0.66

och

0.64

IME

0.64

ajor

0.63

agy

0.62

ãĤ¡

0.61

 deriv

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.