INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

bernatorial

-0.90

isance

-0.80

illes

-0.77

itaire

-0.74

anamo

-0.74

eries

-0.73

aea

-0.72

itatively

-0.72

heny

-0.71

onial

-0.71

POSITIVE LOGITS

BRE

0.79

MAN

0.79

wolves

0.79

About

0.73

CLE

0.73

Untitled

0.73

POL

0.72

ÃĹ

0.69

BE

0.69

ANN

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.