INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ZA

-0.67

Reviewer

-0.67

avior

-0.66

IZ

-0.65

WARE

-0.64

âķĲâķĲ

-0.63

tained

-0.63

WAY

-0.62

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.62

Haunted

-0.62

POSITIVE LOGITS

ilus

0.76

ahime

0.73

oche

0.69

ggles

0.67

 Jagu

0.67

 TAMADRA

0.66

aris

0.64

emale

0.64

aux

0.63

RPG

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.