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

DragonMagazine

-0.76

atari

-0.69

 DRAGON

-0.67

uez

-0.65

icz

-0.64

advertising

-0.63

FTA

-0.62

atti

-0.62

ersen

-0.62

fired

-0.62

POSITIVE LOGITS

method

0.71

atics

0.67

 extraction

0.61

oor

0.59

 scal

0.59

grass

0.59

 Amer

0.59

 Shock

0.57

atown

0.57

ewitness

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.