INDEX

Explanations

information related to procedural steps or processes for proposing and reviewing community-focused projects

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.09

1:0.02

2:0.31

3:0.06

4:0.09

5:0.10

6:0.03

7:0.02

8:0.06

9:0.09

10:0.05

11:0.03

Negative Logits

ishes

-1.43

MSN

-1.12

ido

-1.09

 Monkey

-1.09

 Mahjong

-1.08

atche

-1.08

 slack

-1.07

 Fairy

-1.07

 Meow

-1.03

ansas

-1.03

POSITIVE LOGITS

\\\\\\\\

1.29

CLASSIFIED

1.29

��

1.27

sonian

1.21

 congr

1.20

 synopsis

1.18

 parity

1.15

pec

1.14

 Centauri

1.13

mosp

1.10

Activations Density 0.011%

information related to procedural steps or processes for proposing and reviewing community-focused projects

No Known Activations