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

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.09

11:0.09

Negative Logits

held

-1.34

sn

-1.34

 Arms

-1.32

SOU

-1.30

Bre

-1.27

 tranquil

-1.24

 Tatt

-1.23

NOR

-1.22

iar

-1.22

aft

-1.19

POSITIVE LOGITS

��

1.64

━

1.57

 incent

1.57

itect

1.55

═

1.52

kees

1.51

enegger

1.51

conservancy

1.47

krit

1.39

 entrepreneurship

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.