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

 Barcl

-0.69

 Bung

-0.69

©¶æ

-0.68

Ĥİ

-0.68

oldown

-0.67

©¶æ¥µ

-0.66

*:

-0.66

ģ«

-0.63

agara

-0.63

 Cortana

-0.62

POSITIVE LOGITS

Reviewer

0.72

iating

0.62

Pub

0.62

Merit

0.62

inflamm

0.60

 decre

0.60

iated

0.59

 sten

0.58

DIT

0.56

 crit

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.