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

zona

-0.85

abee

-0.77

leon

-0.68

ELY

-0.68

lain

-0.67

 akin

-0.65

imated

-0.64

quin

-0.63

CLA

-0.63

ivalent

-0.62

POSITIVE LOGITS

uyomi

1.07

ulhu

1.05

APTER

0.82

ruciating

0.80

ktop

0.80

utsu

0.78

ModLoader

0.75

ersen

0.72

cffff

0.72

 Gutenberg

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.