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

0:0.09

1:0.07

2:0.09

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 Mamm

-1.53

affiliated

-1.42

thood

-1.39

ngth

-1.39

ISS

-1.39

 Tackle

-1.37

aughtered

-1.33

'."

-1.33

 Mouth

-1.32

 Fitness

-1.30

POSITIVE LOGITS

��

1.56

Jet

1.46

 flared

1.41

ILLE

1.37

 wedge

1.36

 painter

1.35

gui

1.33

aro

1.32

otive

1.32

ROM

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.