INDEX

Explanations

punctuation marks and new line breaks in the text

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

0:0.12

1:0.03

2:0.05

3:0.04

4:0.05

5:0.03

6:0.24

7:0.04

8:0.11

9:0.19

10:0.02

11:0.04

Negative Logits

 Palest

-4.09

 Titanic

-3.62

 subord

-3.42

 tsun

-3.31

ズ

-3.25

 compan

-3.22

-3.20

cat

-3.20

 comet

-3.17

 Puerto

-3.15

POSITIVE LOGITS

 Griffith

11.31

Gr

5.78

 Grimes

4.96

 Grace

4.72

 Forrest

4.68

Gaw

4.31

 Grind

4.29

gr

4.25

 Griffin

4.23

 Douglas

4.08

Activations Density 0.001%

punctuation marks and new line breaks in the text

No Comments

No Known Activations