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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

«

-0.72

 exting

-0.72

endez

-0.67

\\\\\\\\

-0.64

)))

-0.63

ãĤ´

-0.63

CHA

-0.62

actionDate

-0.62

Ã¡n

-0.61

 bitten

-0.61

POSITIVE LOGITS

ractions

0.74

Roberts

0.72

mes

0.69

olars

0.67

visor

0.64

 peripher

0.64

ervatives

0.63

 distinguished

0.63

competitive

0.62

peak

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.