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

olithic

-0.78

chwitz

-0.74

atial

-0.67

elligence

-0.67

ometer

-0.62

imeter

-0.61

BA

-0.60

ometers

-0.60

GM

-0.59

OUS

-0.59

POSITIVE LOGITS

 Chero

0.69

blow

0.68

 Coral

0.66

roth

0.66

 mosquit

0.65

ãĥķãĤ©

0.65

 Carbuncle

0.65

 Neph

0.64

rolling

0.63

 tides

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.