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

bestos

-0.83

etus

-0.80

anchester

-0.79

soever

-0.72

EDT

-0.67

owship

-0.67

resp

-0.66

anwhile

-0.66

ound

-0.65

 Â®

-0.65

POSITIVE LOGITS

å°Ĩ

0.70

was

0.65

 finish

0.63

 reviewers

0.62

Feature

0.62

Stars

0.61

 brisk

0.60

Pin

0.59

shine

0.58

Overall

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.