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

 Disciple

-0.75

TIT

-0.69

 Infinity

-0.68

 RAND

-0.67

 treasure

-0.67

 hints

-0.64

 Legacy

-0.64

 Shrine

-0.64

 whispers

-0.63

 Mercenary

-0.62

POSITIVE LOGITS

iol

0.75

ernels

0.73

cin

0.70

adjusted

0.69

igating

0.68

ovich

0.68

ieri

0.67

ability

0.67

safe

0.67

journal

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.