INDEX

Explanations

dates and numbers related to events and statistics

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.02

1:0.03

2:0.06

3:0.29

4:0.04

5:0.02

6:0.11

7:0.16

8:0.04

9:0.04

10:0.09

11:0.07

Negative Logits

 grit

-1.19

igans

-1.18

 Goose

-1.06

 Cutler

-1.04

 Exile

-1.01

 trout

-0.98

 retreat

-0.97

 Purg

-0.96

 Laos

-0.96

 Piet

-0.95

POSITIVE LOGITS

DragonMagazine

1.34

�

1.33

NESS

1.18

RANT

1.18

 Jury

1.15

NPR

1.15

Interstitial

1.14

Initialized

1.05

UV

1.05

PP

1.05

Activations Density 0.019%

dates and numbers related to events and statistics

No Comments

No Known Activations