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

ModLoader

-0.86

iquid

-0.72

 Doodle

-0.67

 brisk

-0.66

runs

-0.64

ORED

-0.64

 originals

-0.64

 Chronicles

-0.63

ogle

-0.63

 Surviv

-0.62

POSITIVE LOGITS

ommod

0.90

alk

0.83

array

0.73

hot

0.72

selves

0.71

ole

0.71

ahn

0.70

large

0.69

Transfer

0.68

wage

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.