INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Distribut

-0.73

 Vers

-0.73

 Pole

-0.73

ulously

-0.71

visor

-0.71

ãĤ¸

-0.70

iler

-0.70

visors

-0.69

 Contribut

-0.69

 Democr

-0.68

POSITIVE LOGITS

alore

0.71

 spectrum

0.70

actionDate

0.70

ADRA

0.70

NM

0.68

soDeliveryDate

0.68

CHAT

0.67

 sclerosis

0.67

 seizures

0.66

 visas

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.