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

-0.86

Newsletter

-0.79

 Frie

-0.79

 GOODMAN

-0.74

 Ferr

-0.72

ridor

-0.70

 Inher

-0.69

 Ambro

-0.69

berry

-0.66

Draft

-0.66

POSITIVE LOGITS

ishable

0.67

sun

0.64

served

0.63

terday

0.63

OSH

0.62

kat

0.60

avorite

0.60

 wildfire

0.59

isable

0.59

itary

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.