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

ederation

-0.83

 reper

-0.79

 reckoning

-0.76

zzle

-0.75

urat

-0.75

atta

-0.73

orthy

-0.72

 muzzle

-0.71

arial

-0.69

ctica

-0.68

POSITIVE LOGITS

ãĥĻ

0.68

gart

0.63

meier

0.62

 Instruments

0.62

 Fake

0.61

UTH

0.60

Companies

0.60

cham

0.59

Bey

0.58

Teen

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.