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

adian

-0.77

adena

-0.72

nesota

-0.70

aday

-0.69

Adapt

-0.68

obe

-0.68

 advoc

-0.66

 Doodle

-0.65

aid

-0.65

MIT

-0.65

POSITIVE LOGITS

 Spears

0.68

 Records

0.64

"],"

0.63

 âĢİ

0.62

 Thief

0.62

Staff

0.62

 padded

0.62

 Strait

0.60

 Flavoring

0.60

'>

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.