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

ateur

-0.81

oxide

-0.76

 conduc

-0.75

Ń·

-0.74

nikov

-0.74

ateurs

-0.73

adiator

-0.73

inki

-0.67

inctions

-0.67

aryl

-0.66

POSITIVE LOGITS

 Saud

0.67

 Rout

0.67

 manoeuv

0.66

 Bout

0.66

Construct

0.65

Magikarp

0.64

cour

0.63

TEXTURE

0.63

RP

0.62

Di

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.