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

imaru

-0.76

 Jinn

-0.68

BP

-0.68

.–

-0.62

hai

-0.62

aghetti

-0.62

 bushes

-0.61

aneers

-0.61

esp

-0.60

æ©Ł

-0.60

POSITIVE LOGITS

 elig

0.70

tarian

0.69

 Plenty

0.65

hedral

0.61

agher

0.60

 boycot

0.58

mans

0.57

allion

0.57

Ħ¢

0.56

worthy

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.