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

0:0.07

1:0.06

2:0.09

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.10

Negative Logits

 Excellence

-1.64

 Transparency

-1.51

 Noir

-1.49

afort

-1.47

],"

-1.40

 Zeit

-1.39

 belie

-1.38

aucas

-1.35

 Wash

-1.33

aturday

-1.32

POSITIVE LOGITS

覚醒

1.68

egg

1.54

 loads

1.35

cycl

1.35

erto

1.34

tri

1.33

mods

1.32

 surviving

1.32

 drummer

1.32

 rider

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.