INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 prelim

-0.70

×ķ

-0.66

 starters

-0.64

 judge

-0.63

 Rampage

-0.62

 mileage

-0.62

Putin

-0.61

CU

-0.60

WER

-0.60

 price

-0.59

POSITIVE LOGITS

ascript

0.86

earable

0.86

ittens

0.83

ingen

0.77

haar

0.77

agy

0.76

imet

0.75

rust

0.75

itivity

0.74

arton

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.