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

DragonMagazine

-0.79

Naz

-0.78

Gate

-0.70

LCS

-0.70

Sham

-0.69

artifacts

-0.67

antis

-0.67

outing

-0.67

TextColor

-0.66

anism

-0.66

POSITIVE LOGITS

bang

0.67

psy

0.66

 Geographic

0.64

otal

0.63

 Tiger

0.62

 Clever

0.61

 DIRECT

0.60

sonian

0.60

 Manufacturer

0.60

 familiar

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.