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

 unaff

-0.65

tis

-0.65

'';

-0.62

 Unloaded

-0.61

 wors

-0.60

espie

-0.60

 effected

-0.59

 stitch

-0.59

 Shutterstock

-0.58

ens

-0.57

POSITIVE LOGITS

eday

0.76

 Saiyan

0.68

Bird

0.68

æ©

0.67

uci

0.65

egu

0.64

afer

0.63

afety

0.63

ãĥ´ãĤ¡

0.63

aiman

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.