INDEX

Explanations

phrases that express uncertainty or contemplation about actions and decisions

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

0:0.03

1:0.03

2:0.07

3:0.24

4:0.02

5:0.07

6:0.02

7:0.07

8:0.02

9:0.02

10:0.32

11:0.03

Negative Logits

significant

-2.29

 counterpart

-2.19

isite

-2.16

 predecessor

-2.10

paralle

-2.09

 exceeds

-2.05

 imped

-1.99

grave

-1.92

 Yose

-1.86

 detriment

-1.80

POSITIVE LOGITS

 calmly

2.74

 pretend

2.45

 politely

2.41

 quietly

2.37

 stuff

2.34

 bullshit

2.21

 blah

2.21

 crap

2.20

 shit

2.19

 shrug

2.18

Activations Density 0.323%

phrases that express uncertainty or contemplation about actions and decisions

No Comments

No Known Activations