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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ģ

-0.75

¼

-0.73

£

-0.70

Ĥ

-0.69

ħ

-0.67

abella

-0.66

Ĩ

-0.66

Ĭ

-0.65

Ħ

-0.65

ģ«

-0.65

POSITIVE LOGITS

 mobs

0.68

 react

0.64

asking

0.63

ox

0.62

ockey

0.61

iets

0.61

Mog

0.60

 contag

0.60

 spontaneously

0.60

 reacting

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.