INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

âĹ¼

-0.99

catentry

-0.91

inding

-0.84

CLASSIFIED

-0.75

ALSE

-0.74

ochet

-0.74

ategory

-0.73

opian

-0.72

HR

-0.72

ħĭ

-0.70

POSITIVE LOGITS

esville

0.73

 mobs

0.72

inelli

0.67

 passers

0.67

 villages

0.64

 Shant

0.63

 counties

0.62

ihu

0.61

eon

0.60

 towns

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.