INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 princ

-0.72

 comprom

-0.68

 Competitive

-0.66

issance

-0.65

 ceremonies

-0.64

 Martial

-0.63

«ĺ

-0.62

 Mahjong

-0.61

oha

-0.60

 Micha

-0.59

POSITIVE LOGITS

Fill

0.73

Attach

0.73

Wheel

0.71

Spread

0.71

Fish

0.70

weights

0.69

ESA

0.68

Bed

0.67

rones

0.67

Eth

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.