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

1:0.08

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 Guant

-1.49

umb

-1.40

missing

-1.38

 warheads

-1.32

ATHER

-1.29

Ros

-1.29

Lib

-1.29

 Sergeant

-1.28

 trib

-1.25

Tre

-1.25

POSITIVE LOGITS

 Pixel

1.68

 Patreon

1.67

agogue

1.55

isphere

1.54

ggle

1.52

 financially

1.45

 participating

1.44

iggurat

1.42

endars

1.40

 tailor

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.