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

ragon

-0.75

rael

-0.73

 Machina

-0.66

aimon

-0.66

oto

-0.65

galitarian

-0.63

yright

-0.62

romeda

-0.62

yl

-0.62

yd

-0.61

POSITIVE LOGITS

tesy

0.73

SER

0.71

RESULTS

0.71

ANCE

0.65

SOURCE

0.64

VICE

0.64

toe

0.64

ï¸

0.63

lean

0.62

ANC

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.