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

ignty

-0.74

asio

-0.66

ounds

-0.65

 Blasio

-0.64

 Markets

-0.64

WAR

-0.62

lished

-0.62

 Cancel

-0.61

ulia

-0.61

 Move

-0.60

POSITIVE LOGITS

PIN

0.74

 redeem

0.73

 dormant

0.67

iary

0.66

nas

0.64

 batter

0.64

 Palmer

0.63

pil

0.62

 slightest

0.61

Yor

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.