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

Head Attr Weights

0:0.08

1:0.07

2:0.09

3:0.08

4:0.07

5:0.09

6:0.07

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

reach

-1.49

iers

-1.48

ridges

-1.37

adr

-1.34

rid

-1.30

States

-1.28

LOD

-1.28

rooms

-1.27

iker

-1.26

agents

-1.24

POSITIVE LOGITS

 unden

1.69

═

1.52

 Aires

1.48

NYSE

1.41

 charism

1.38

 Learns

1.38

zzo

1.37

▬▬

1.36

++++++++

1.36

�

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.