INDEX

Explanations

titles and positions related to organizational roles and leadership

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

1:0.02

2:0.07

3:0.09

4:0.02

5:0.05

6:0.07

7:0.22

8:0.05

9:0.07

10:0.05

11:0.22

Negative Logits

onies

-1.45

ateral

-1.20

 fleeting

-1.20

 firsthand

-1.20

fman

-1.18

 semblance

-1.15

rawdownloadcloneembedreportprint

-1.15

ptions

-1.15

 Pieces

-1.14

anqu

-1.13

POSITIVE LOGITS

iHUD

1.51

 Ernst

1.48

warn

1.41

 Vall

1.39

 Tiff

1.33

��極

1.31

 Shank

1.28

WARN

1.27

 Warn

1.27

 Miche

1.25

Activations Density 0.117%

titles and positions related to organizational roles and leadership

No Comments

No Known Activations