INDEX

Explanations

advice and guidance related to various topics

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

0:0.26

1:0.03

2:0.23

3:0.07

4:0.04

5:0.07

6:0.04

7:0.04

8:0.03

9:0.05

10:0.06

11:0.02

Negative Logits

 liqu

-2.48

 hangar

-2.48

 crane

-2.47

Seg

-2.44

 Exhibition

-2.41

 exhibition

-2.37

 segreg

-2.33

shut

-2.31

 staging

-2.27

ney

-2.22

POSITIVE LOGITS

 recommending

5.35

 advice

5.31

 Advice

5.10

 advises

5.07

 recommendations

5.01

 recommendation

4.87

 advising

4.81

 advise

4.65

 advised

4.44

 recommends

4.39

Activations Density 0.063%

advice and guidance related to various topics

No Comments

No Known Activations