INDEX

Explanations

references to collaboration and collective effort in artistic projects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.03

2:0.04

3:0.05

4:0.03

5:0.04

6:0.11

7:0.04

8:0.04

9:0.46

10:0.02

11:0.04

Negative Logits

 Beth

-3.54

 Donna

-3.52

 Lori

-3.45

nah

-3.12

 Finn

-3.11

itta

-3.11

itt

-3.09

 oblig

-3.02

 Morty

-2.99

 Abraham

-2.91

POSITIVE LOGITS

7.64

6.64

6.42

Xen

5.94

XL

5.61

xx

5.58

xf

5.48

Pix

5.46

Xi

5.44

XX

5.42

Activations Density 0.127%

references to collaboration and collective effort in artistic projects

No Comments

No Known Activations