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

0:0.08

1:0.09

2:0.08

3:0.08

4:0.07

5:0.07

6:0.09

7:0.08

8:0.06

9:0.09

10:0.08

11:0.08

Negative Logits

mens

-2.94

owers

-2.89

Dug

-2.57

shr

-2.55

 workplaces

-2.43

iders

-2.42

pora

-2.35

ower

-2.29

riages

-2.29

›

-2.24

POSITIVE LOGITS

natureconservancy

2.81

sbm

2.69

imentary

2.54

 Penguin

2.42

 Arkham

2.40

assic

2.39

ardi

2.39

Sequ

2.39

inventoryQuantity

2.38

ffen

2.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.