INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 diction

-0.80

okÃ©

-0.76

ogue

-0.70

 essays

-0.67

 Pett

-0.66

boards

-0.64

elvet

-0.64

venants

-0.63

ebook

-0.63

 stakeholders

-0.63

POSITIVE LOGITS

strings

0.77

sis

0.73

zzy

0.70

etheless

0.70

 Rena

0.69

rique

0.68

ãĥĺãĥ©

0.65

igma

0.62

buster

0.62

handled

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.