INDEX

Explanations

phrases related to evaluations or comparisons of performance

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

0:0.02

1:0.01

2:0.17

3:0.24

4:0.11

5:0.02

6:0.03

7:0.08

8:0.06

9:0.07

10:0.09

11:0.05

Negative Logits

 Cheong

-1.55

*)

-1.40

ake

-1.38

*,

-1.36

aves

-1.35

%);

-1.35

quartered

-1.33

Own

-1.29

���

-1.28

 Draper

-1.26

POSITIVE LOGITS

Finish

1.72

 hopefully

1.69

 someday

1.63

geist

1.52

 goodness

1.47

 next

1.44

 glim

1.43

pie

1.35

Hopefully

1.35

Marvel

1.34

Activations Density 0.061%

phrases related to evaluations or comparisons of performance

No Comments

No Known Activations