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

iot

-0.72

Ü

-0.71

Users

-0.71

galitarian

-0.69

atory

-0.69

ateurs

-0.69

ather

-0.68

ersive

-0.68

IRE

-0.67

Serv

-0.66

POSITIVE LOGITS

QC

0.74

 Strait

0.70

 Toledo

0.70

 Fiat

0.66

pen

0.63

 crossing

0.62

 Sinai

0.62

 Crusade

0.62

 Powell

0.61

 Ceres

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.