INDEX

Explanations

No Explanations Found

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.07

4:0.07

5:0.08

6:0.09

7:0.08

8:0.07

9:0.09

10:0.08

11:0.09

Negative Logits

 fluoride

-1.74

 surf

-1.54

 fluor

-1.48

 meditation

-1.38

 trans

-1.38

 filtering

-1.38

 tooth

-1.35

 cleansing

-1.34

 mindfulness

-1.33

 Trayvon

-1.33

POSITIVE LOGITS

��極

1.65

 Economy

1.34

_>

1.33

 Pengu

1.32

 Marketable

1.31

 Clash

1.29

ertain

1.28

___

1.27

 Logged

1.27

 Mathemat

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.