INDEX

Explanations

elements related to choice and selection processes in various contexts

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

2:0.03

3:0.04

4:0.06

5:0.16

6:0.04

7:0.05

8:0.02

9:0.38

10:0.02

11:0.09

Negative Logits

displayText

-2.81

aken

-2.43

gered

-2.37

cknowled

-2.35

Published

-2.34

akening

-2.28

oing

-2.26

gging

-2.26

leasing

-2.23

sted

-2.17

POSITIVE LOGITS

 winner

2.90

 whichever

2.89

 BEST

2.73

 whom

2.64

 wisely

2.60

 each

2.56

 Which

2.55

 winners

2.52

 closest

2.47

 standout

2.46

Activations Density 0.269%

elements related to choice and selection processes in various contexts

No Comments

No Known Activations