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

ricanes

-0.77

dayName

-0.66

concept

-0.66

 knack

-0.66

elsius

-0.63

 Cursed

-0.62

inia

-0.62

occ

-0.61

culated

-0.61

lington

-0.59

POSITIVE LOGITS

ĺħ

0.73

DragonMagazine

0.70

ership

0.68

galitarian

0.67

izational

0.66

FM

0.63

 Struggle

0.62

itness

0.62

 carriage

0.61

EVA

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.