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

 bluff

-0.72

ptions

-0.68

Accessory

-0.67

cellent

-0.66

hyde

-0.65

ļéĨĴ

-0.64

cius

-0.62

 prevail

-0.61

tesy

-0.60

SPONSORED

-0.60

POSITIVE LOGITS

essel

0.69

foreseen

0.66

resh

0.66

affected

0.66

uner

0.64

engers

0.63

itudes

0.62

source

0.60

ains

0.60

raction

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.