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

edIn

-0.72

 referen

-0.71

erker

-0.66

 intrins

-0.64

¬¼

-0.63

pees

-0.63

quo

-0.60

 rall

-0.60

 Minotaur

-0.60

treated

-0.59

POSITIVE LOGITS

 Flickr

0.67

 Homes

0.66

 Records

0.65

ty

0.63

 Bond

0.63

Torrent

0.62

 imprint

0.60

 Message

0.60

 Mail

0.59

ãĤ¼ãĤ¦ãĤ¹

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.