INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

NRS

-0.73

roit

-0.69

abase

-0.68

yond

-0.67

ATHER

-0.67

bris

-0.64

enf

-0.63

rf

-0.62

bnb

-0.61

¥

-0.61

POSITIVE LOGITS

Jed

0.79

ombies

0.76

å§«

0.72

Oo

0.68

 cookie

0.65

aceae

0.65

omp

0.62

ummer

0.61

 preferring

0.61

ickers

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.