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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

orn

-2.55

 mont

-2.52

 fasc

-2.52

 monarch

-2.50

fax

-2.47

 Democr

-2.47

 substr

-2.42

 subp

-2.40

 bend

-2.38

 marqu

-2.36

POSITIVE LOGITS

 SNAP

2.88

isSpecialOrderable

2.70

aign

2.66

 Soup

2.65

Employ

2.60

okia

2.49

Cra

2.49

 Shopping

2.46

GST

2.45

bucks

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.