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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

estate

-1.61

addons

-1.54

eatures

-1.42

 Leilan

-1.39

Emer

-1.36

bay

-1.30

cffffcc

-1.30

 roared

-1.28

iera

-1.28

profits

-1.27

POSITIVE LOGITS

 Painting

1.66

 Dove

1.47

BET

1.36

 Gins

1.35

 TEXT

1.34

 pagan

1.33

Wax

1.32

 Bees

1.32

artisan

1.29

�

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.