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

matter

-0.75

İĭ

-0.71

oran

-0.70

 Matter

-0.69

assy

-0.68

 Ferry

-0.67

 Lama

-0.64

jay

-0.63

zik

-0.63

inx

-0.62

POSITIVE LOGITS

alloc

0.70

 claimants

0.69

merce

0.67

ernels

0.66

Interstitial

0.63

 isEnabled

0.63

 tremend

0.62

EG

0.62

odied

0.61

reement

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.