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

orf

-0.77

mosp

-0.75

omen

-0.75

ensable

-0.74

ythm

-0.72

heid

-0.71

ffen

-0.70

jen

-0.68

REAM

-0.67

estic

-0.66

POSITIVE LOGITS

 rall

0.82

 elig

0.71

 Shutterstock

0.67

Byz

0.65

 clust

0.64

 veter

0.63

 Macedonia

0.63

istani

0.62

 paramed

0.62

 tremend

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.