INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.08

4:0.09

5:0.08

6:0.09

7:0.07

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

�

-2.90

soDeliveryDate

-2.77

License

-2.69

Blu

-2.62

Lic

-2.60

Lic

-2.60

Url

-2.50

Newsletter

-2.49

Linux

-2.41

Spons

-2.39

POSITIVE LOGITS

 damp

2.61

 chewing

2.52

 consequential

2.48

 acutely

2.44

 Roose

2.44

 humid

2.35

 primed

2.34

 observational

2.33

 conflicted

2.31

 cognitive

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.