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

etheless

-0.83

»Ĵ

-0.71

 confir

-0.71

ĩ

-0.70

ospital

-0.68

ĨĴ

-0.68

ahime

-0.67

çĶ°

-0.67

orde

-0.67

¶ħ

-0.67

POSITIVE LOGITS

 Instruct

0.69

Fei

0.66

 Spur

0.66

Eck

0.63

itiveness

0.63

kaya

0.62

flo

0.62

trap

0.61

Fu

0.61

Poo

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.