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

 clipboard

-0.64

 embr

-0.64

ophobia

-0.62

Cla

-0.61

 eviction

-0.61

 arrogant

-0.59

FP

-0.58

 pigeon

-0.58

 deportation

-0.58

 homophobic

-0.57

POSITIVE LOGITS

leck

0.82

soDeliveryDate

0.78

FTWARE

0.73

enter

0.73

 Marketable

0.72

foundland

0.71

asca

0.71

une

0.70

relative

0.68

inals

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.