INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Round

-0.94

Hello

-0.70

fold

-0.69

erous

-0.68

OUT

-0.67

Â·Â·

-0.67

Zen

-0.67

++;

-0.66

ertodd

-0.65

Pages

-0.65

POSITIVE LOGITS

 behavi

0.71

 Clancy

0.68

ecd

0.68

 dere

0.67

ali

0.65

 Chern

0.65

au

0.64

 entitlement

0.63

 Caesar

0.63

 discretion

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.