INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.08

1:0.06

2:0.09

3:0.06

4:0.09

5:0.08

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

)=(

-1.96

DragonMagazine

-1.86

ALSE

-1.83

Accessory

-1.74

usalem

-1.69

��

-1.66

irlfriend

-1.66

undreds

-1.63

 Bulg

-1.62

ItemImage

-1.61

POSITIVE LOGITS

onomic

1.59

 governing

1.51

 Discipline

1.44

icators

1.43

 annex

1.39

 Briggs

1.39

ilion

1.37

 Conserv

1.35

 declaration

1.34

acity

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.