INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

estamp

-0.71

ifax

-0.69

omore

-0.69

aukee

-0.69

 Wonders

-0.68

 Perkins

-0.67

agraph

-0.64

.ï¿½

-0.63

sylv

-0.63

ÃĤ

-0.61

POSITIVE LOGITS

rez

0.76

Metal

0.73

metal

0.72

sword

0.69

skirts

0.68

alions

0.68

ouring

0.67

riz

0.67

weights

0.66

amental

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.