INDEX

Explanations

punctuation and formatting elements in 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

0:0.05

1:0.06

2:0.05

3:0.03

4:0.05

5:0.04

6:0.14

7:0.05

8:0.09

9:0.13

10:0.04

11:0.24

Negative Logits

 droid

-3.25

 toddler

-2.88

 Droid

-2.83

android

-2.83

 devs

-2.79

 Jets

-2.74

stellar

-2.73

 puppy

-2.72

 Seas

-2.63

 Tooth

-2.63

POSITIVE LOGITS

Ã

7.98

â

7.38

Â

6.98

Í

5.95

ã

5.39

�

5.19

ô

5.06

«

5.04

«

4.86

û

4.81

Activations Density 0.003%

punctuation and formatting elements in text

No Comments

No Known Activations