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

 Mens

-0.72

 Xuan

-0.71

CLASSIFIED

-0.70

 merch

-0.67

 cumbers

-0.66

 reckoned

-0.66

 Amon

-0.64

 soph

-0.63

Beast

-0.62

 suspic

-0.62

POSITIVE LOGITS

vic

0.79

rag

0.77

oute

0.72

vg

0.71

opez

0.70

indal

0.68

rir

0.68

orsi

0.68

miah

0.67

fr

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.