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

 confir

-0.71

 unsur

-0.70

uala

-0.70

 cryst

-0.68

adelphia

-0.67

ģ«

-0.66

PDATE

-0.65

 Patient

-0.64

ĨĴ

-0.62

 rall

-0.62

POSITIVE LOGITS

Äĩ

0.83

apple

0.75

aja

0.71

illard

0.71

vious

0.68

idium

0.68

busters

0.68

ico

0.67

eki

0.67

oe

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.