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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Twe

-0.82

é¾įå

-0.75

eteen

-0.72

sup

-0.71

WAR

-0.70

anz

-0.68

aturdays

-0.67

ultz

-0.67

 syndrome

-0.65

intendo

-0.63

POSITIVE LOGITS

 Claw

0.79

 Predator

0.76

clave

0.74

 Piercing

0.72

 Natural

0.68

 Planetary

0.68

aminer

0.65

 Fusion

0.65

staking

0.65

dds

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.