INDEX

Explanations

phrases related to decision-making processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

0:0.03

1:0.01

2:0.13

3:0.05

4:0.06

5:0.06

6:0.16

7:0.03

8:0.10

9:0.03

10:0.21

11:0.08

Negative Logits

コ

-1.55

 chic

-1.54

atinum

-1.53

cair

-1.52

anan

-1.50

 Latvia

-1.48

gyn

-1.48

 Izan

-1.44

uitive

-1.44

 Saint

-1.43

POSITIVE LOGITS

respons

1.83

 predic

1.78

 deliberations

1.75

 decisions

1.75

yrus

1.73

 competence

1.66

 dealings

1.64

 dissatisf

1.63

ivity

1.61

inton

1.60

Activations Density 0.001%

phrases related to decision-making processes

No Comments

No Known Activations