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

ens

-0.78

eur

-0.72

bats

-0.64

 crow

-0.64

 ensued

-0.61

 seaw

-0.61

 Shea

-0.60

 Pelicans

-0.59

 impunity

-0.58

 Haram

-0.57

POSITIVE LOGITS

ebted

0.76

ipop

0.75

ipolar

0.72

ileged

0.72

STEP

0.68

ividually

0.67

bare

0.64

icrobial

0.63

arma

0.62

leaf

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.