INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

fulness

-0.79

field

-0.71

tering

-0.68

chest

-0.68

fields

-0.67

ographical

-0.64

phe

-0.63

 flavour

-0.62

 souven

-0.62

bread

-0.62

POSITIVE LOGITS

1.11

é¾įå

0.77

0.74

 Includes

0.69

 Recommended

0.68

ä¸Ĭ

0.67

 Allows

0.67

 Aires

0.67

 Exile

0.66

 Vengeance

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.