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

4:0.08

5:0.09

6:0.07

7:0.09

8:0.09

9:0.07

10:0.06

11:0.08

Negative Logits

CTV

-1.60

uyomi

-1.41

rouch

-1.33

igel

-1.29

illian

-1.28

ette

-1.24

 Franch

-1.22

rue

-1.20

MON

-1.20

obb

-1.19

POSITIVE LOGITS

":["

1.23

 Pale

1.20

 Goddess

1.20

ゼウス

1.15

 interpreter

1.14

cks

1.14

 proletariat

1.10

 Assy

1.09

 reconstruction

1.09

)]

1.08

Activations Density 0.000%

No Known Activations

This feature has no known activations.