INDEX

Explanations

phrases related to contributions and recognition

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.02

1:0.01

2:0.05

3:0.06

4:0.09

5:0.03

6:0.07

7:0.31

8:0.03

9:0.03

10:0.11

11:0.13

Negative Logits

Shipping

-1.56

Agent

-1.50

RELATED

-1.50

 contracted

-1.40

CHAT

-1.32

ゴン

-1.31

actionDate

-1.31

RANT

-1.30

 invoice

-1.27

 consent

-1.25

POSITIVE LOGITS

 Literature

1.56

 Perspect

1.56

 Hast

1.48

ener

1.39

 Proceedings

1.35

 Architecture

1.30

vae

1.29

 Commentary

1.27

 Insp

1.26

 Buddhism

1.26

Activations Density 0.004%

phrases related to contributions and recognition

No Known Activations