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

anian

-0.76

accompan

-0.73

aghan

-0.70

itaire

-0.68

onomic

-0.68

ipers

-0.67

cknow

-0.66

autions

-0.65

onom

-0.65

istor

-0.64

POSITIVE LOGITS

 Aber

0.68

Hud

0.64

Elk

0.64

soDeliveryDate

0.63

 indirectly

0.63

Mun

0.63

 Bung

0.62

Zub

0.61

 Jama

0.60

Zup

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.