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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amera

-0.74

aniel

-0.69

ensen

-0.68

 reproduction

-0.66

 contraction

-0.65

anasia

-0.65

 printing

-0.64

^^

-0.63

BYU

-0.62

iquid

-0.62

POSITIVE LOGITS

iably

0.73

 fitt

0.67

Interstitial

0.67

NetMessage

0.66

 glim

0.66

lite

0.64

estones

0.64

 Frie

0.63

Ori

0.63

 Dare

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.