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

tackle

-0.72

iversary

-0.66

catentry

-0.66

eday

-0.65

wig

-0.64

cks

-0.63

cow

-0.62

gear

-0.61

gee

-0.61

cknow

-0.61

POSITIVE LOGITS

 DRAGON

0.67

Story

0.67

.$

0.66

ragon

0.65

 Rowling

0.65

ateral

0.64

Sax

0.63

itism

0.63

puted

0.62

Gry

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.