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

é¾įå¥ĳå£«

-0.87

 Blasio

-0.68

Eag

-0.67

 Cumm

-0.64

 Coinbase

-0.63

 postpone

-0.63

 encour

-0.63

 introdu

-0.62

 preval

-0.61

 Burlington

-0.61

POSITIVE LOGITS

zag

0.70

 perished

0.68

tur

0.66

anium

0.65

wered

0.65

doms

0.65

fur

0.64

ses

0.62

stan

0.62

inus

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.