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

assets

-0.76

retion

-0.65

SEC

-0.64

":["

-0.62

atives

-0.62

 oneself

-0.61

pent

-0.61

æī

-0.61

Ore

-0.59

-(

-0.58

POSITIVE LOGITS

wagen

0.82

 anew

0.74

marked

0.68

 Reloaded

0.67

 Reborn

0.66

 Libre

0.64

 challeng

0.64

byn

0.63

»Ĵ

0.63

 logger

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.