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

ensical

-0.72

-0.68

vironment

-0.63

ishi

-0.62

ori

-0.61

Planet

-0.58

-0.57

<+

-0.57

 Robot

-0.57

ategy

-0.56

POSITIVE LOGITS

sonian

0.84

soDeliveryDate

0.81

aspers

0.74

 burgl

0.73

laws

0.73

spot

0.69

vich

0.69

 Leilan

0.68

flush

0.66

Offline

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.