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

rious

-0.82

ascript

-0.73

arnaev

-0.67

 Shak

-0.64

kefeller

-0.62

ionics

-0.61

 Armstrong

-0.61

 Roll

-0.60

quist

-0.60

oker

-0.60

POSITIVE LOGITS

isSpecialOrderable

0.80

lvl

0.72

BU

0.66

yout

0.65

 IMAGES

0.65

]=

0.64

VO

0.63

imgur

0.62

ebook

0.61

FE

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.