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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sect

-0.70

mun

-0.69

appropriate

-0.66

olls

-0.65

lance

-0.65

ites

-0.64

ciples

-0.63

ockets

-0.62

awan

-0.61

Pak

-0.61

POSITIVE LOGITS

aukee

0.83

 destro

0.77

raltar

0.76

atform

0.71

utical

0.70

 sovere

0.70

romeda

0.70

 oceans

0.69

atories

0.67

âĢ¢âĢ¢âĢ¢âĢ¢

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.