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

è¦ļéĨĴ

-0.74

DAQ

-0.67

CoC

-0.66

rosis

-0.66

nm

-0.63

 Nemesis

-0.63

istani

-0.63

>>>>>>>>

-0.62

advertisement

-0.62

Ni

-0.61

POSITIVE LOGITS

terday

0.78

ãĥ¼ãĥ³

0.75

zees

0.74

ape

0.68

ially

0.66

Peb

0.64

eals

0.63

berman

0.62

 Scenes

0.62

uesday

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.