INDEX

Explanations

references to dualities or contrasting concepts

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

0:0.05

1:0.08

2:0.05

3:0.07

4:0.03

5:0.05

6:0.21

7:0.02

8:0.02

9:0.31

10:0.03

11:0.03

Negative Logits

UCT

-3.74

 Borg

-3.70

Raven

-3.56

 Bang

-3.48

Kau

-3.41

Hun

-3.39

umo

-3.36

Reg

-3.25

hun

-3.19

 eleph

-3.17

POSITIVE LOGITS

 Side

6.53

Side

5.97

side

5.55

 side

4.92

 sided

4.76

 sides

4.41

 sidebar

4.37

 sidel

3.73

sided

3.73

CP

3.71

Activations Density 0.004%

references to dualities or contrasting concepts

No Comments

No Known Activations