INDEX

Explanations

contrasting expressions of certainty

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.14

1:0.03

2:0.09

3:0.17

4:0.17

5:0.06

6:0.04

7:0.02

8:0.07

9:0.10

10:0.05

11:0.03

Negative Logits

 ASAP

-1.29

hai

-1.25

 Congratulations

-1.25

ioxide

-1.20

Congratulations

-1.18

orem

-1.14

arta

-1.11

ensions

-1.11

 largeDownload

-1.11

IFA

-1.10

POSITIVE LOGITS

nor

1.93

 anymore

1.93

 anything

1.48

 slightest

1.44

urnal

1.40

 dime

1.39

 ever

1.39

 anywhere

1.38

 whatsoever

1.37

 anybody

1.33

Activations Density 0.010%

contrasting expressions of certainty

No Known Activations