INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

HER

-0.86

ocations

-0.69

LOCK

-0.68

 Collector

-0.68

assian

-0.67

ĨĴ

-0.67

missions

-0.66

²¾

-0.66

ctory

-0.65

Ware

-0.64

POSITIVE LOGITS

aeda

0.78

interrupted

0.66

 Krug

0.65

 Vaugh

0.63

Klu

0.63

gri

0.60

ONSORED

0.58

avorite

0.58

Vaj

0.56

rief

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.