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

 Hebdo

-0.83

Language

-0.71

Ĥª

-0.66

 fung

-0.64

 endings

-0.63

 invari

-0.62

Directory

-0.61

ļéĨĴ

-0.60

aum

-0.60

ESCO

-0.60

POSITIVE LOGITS

sob

0.69

ffee

0.68

thia

0.67

 relieve

0.67

 stay

0.65

 scoop

0.65

 enter

0.64

oby

0.63

 reap

0.63

lug

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.