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

HD

-0.77

winner

-0.76

Helper

-0.73

Definition

-0.71

HR

-0.67

FINE

-0.66

Ho

-0.66

MF

-0.65

 grabs

-0.65

LP

-0.64

POSITIVE LOGITS

 tiss

0.81

bilt

0.78

anwhile

0.73

 Pengu

0.67

nas

0.66

 undercut

0.66

 therap

0.66

grim

0.64

 tubing

0.64

enegger

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.