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

©¶æ

-0.76

amples

-0.74

ĪĴ

-0.69

itol

-0.66

utters

-0.65

 Bull

-0.65

itiz

-0.65

 Rounds

-0.64

 Causes

-0.63

iste

-0.63

POSITIVE LOGITS

yip

0.78

icut

0.73

metry

0.71

ania

0.68

footed

0.67

tten

0.64

achus

0.63

pex

0.62

quartered

0.62

sha

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.