INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Citation

-0.70

SOURCE

-0.68

 âĨĳ

-0.67

 Burnett

-0.67

 ACTIONS

-0.64

 landfall

-0.63

onyms

-0.62

iership

-0.62

opsis

-0.61

 Lazarus

-0.61

POSITIVE LOGITS

sung

0.66

amba

0.65

natureconservancy

0.64

erc

0.63

charg

0.63

gem

0.62

ãĥ

0.62

Tes

0.61

kj

0.60

forums

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.