INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

enhagen

-0.86

chwitz

-0.80

rand

-0.78

kefeller

-0.78

agara

-0.75

aber

-0.74

hani

-0.74

zsche

-0.73

ader

-0.72

bats

-0.71

POSITIVE LOGITS

NG

0.67

MSN

0.65

OTUS

0.61

 launcher

0.58

00000000

0.57

ECO

0.55

Applications

0.55

cms

0.55

Content

0.55

 Azure

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.