INDEX

Explanations

the word "as" used in context

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

Head Attr Weights

0:0.09

1:0.07

2:0.09

3:0.09

4:0.08

5:0.07

6:0.07

7:0.09

8:0.06

9:0.08

10:0.08

11:0.08

Negative Logits

 terminated

-2.56

 Manager

-2.45

 termination

-2.45

 ANGEL

-2.40

 suppliers

-2.40

isodes

-2.37

 DIRECT

-2.35

Secretary

-2.34

 customer

-2.33

Department

-2.31

POSITIVE LOGITS

 Leilan

2.85

��

2.78

NK

2.72

 scatter

2.49

 resurgence

2.43

Notable

2.40

 camouflage

2.40

�

2.39

AMY

2.38

 prosper

2.36

Activations Density 0.000%

the word "as" used in context

No Known Activations