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

NetMessage

-0.83

pots

-0.67

udo

-0.66

WER

-0.65

inks

-0.65

gallery

-0.64

YA

-0.63

rates

-0.62

 Cosponsors

-0.62

emis

-0.62

POSITIVE LOGITS

 course

0.85

 Mysteries

0.70

ortunately

0.64

 Affairs

0.62

 Motor

0.60

@#&

0.59

 Spice

0.59

 Eternity

0.59

 Ment

0.58

 Mission

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.