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

alogy

-0.74

haar

-0.68

WARD

-0.68

swer

-0.67

flix

-0.65

"},{"

-0.64

 Stuff

-0.63

osite

-0.62

yip

-0.61

lins

-0.60

POSITIVE LOGITS

etti

0.73

AMS

0.72

sic

0.65

igated

0.65

CCC

0.65

acc

0.64

 Phant

0.63

igi

0.62

 Booker

0.61

otte

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.