INDEX

Explanations

titles and positions of authority within government and organizational structures

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.01

1:0.01

2:0.12

3:0.05

4:0.12

5:0.03

6:0.10

7:0.24

8:0.02

9:0.04

10:0.09

11:0.11

Negative Logits

NetMessage

-1.64

ppo

-1.44

DragonMagazine

-1.39

 balloons

-1.35

Reviewer

-1.30

 bystand

-1.28

サ

-1.27

pedia

-1.25

 iceberg

-1.23

ワン

-1.23

POSITIVE LOGITS

oshop

1.48

 directing

1.36

ensis

1.33

Yor

1.32

 Commerce

1.23

 Editing

1.23

ña

1.20

division

1.20

 Direction

1.18

 Chemistry

1.16

Activations Density 0.012%

titles and positions of authority within government and organizational structures

No Comments

No Known Activations