INDEX

Explanations

discussions about labor and worker rights, particularly in relation to wages and employment conditions

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

0:0.02

1:0.02

2:0.05

3:0.04

4:0.04

5:0.06

6:0.04

7:0.05

8:0.03

9:0.09

10:0.37

11:0.15

Negative Logits

 airing

-1.55

 reviewer

-1.42

 plagiar

-1.41

 Editorial

-1.35

 Publishing

-1.33

Recipe

-1.32

 reviewers

-1.32

 Readers

-1.31

 Publishers

-1.28

 publisher

-1.27

POSITIVE LOGITS

 occupations

1.67

abilities

1.61

 mobility

1.52

 subsistence

1.42

collar

1.39

emale

1.39

skill

1.37

 Occupations

1.36

abwe

1.35

 skills

1.33

Activations Density 0.119%

discussions about labor and worker rights, particularly in relation to wages and employment conditions

No Comments

No Known Activations