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

raints

-0.80

 erection

-0.74

yton

-0.70

angles

-0.69

:(

-0.68

gie

-0.67

ļéĨĴ

-0.66

ingu

-0.65

aunder

-0.65

inet

-0.65

POSITIVE LOGITS

kefeller

0.66

shr

0.62

SHIP

0.62

Drop

0.60

minist

0.59

 phys

0.59

ahl

0.58

PRESS

0.58

Senior

0.58

bush

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.