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

agos

-0.75

eries

-0.68

oun

-0.67

cephal

-0.66

 frog

-0.65

omination

-0.63

orem

-0.63

paces

-0.63

è¦ļéĨĴ

-0.62

 dough

-0.62

POSITIVE LOGITS

icipated

0.70

pton

0.67

aido

0.65

å§«

0.64

 Inqu

0.64

-+-+

0.63

 Trials

0.62

giene

0.61

apolis

0.61

 Liberties

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.