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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zl

-0.71

nell

-0.67

 leases

-0.67

 coerc

-0.67

 booked

-0.66

 arrang

-0.66

uate

-0.65

 smugg

-0.65

 benefic

-0.65

 employ

-0.64

POSITIVE LOGITS

 Reign

0.72

 SHALL

0.71

TOR

0.69

sword

0.67

 Collector

0.66

Shut

0.66

 Ashes

0.65

Gra

0.64

é»Ĵ

0.64

 Tyrann

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.