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

0:0.09

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.06

7:0.08

8:0.07

9:0.09

10:0.08

11:0.06

Negative Logits

etheless

-1.51

oots

-1.31

 absorbs

-1.28

 Cunning

-1.25

 underestimated

-1.25

�

-1.23

 Boko

-1.22

 plum

-1.17

areth

-1.17

 Niger

-1.14

POSITIVE LOGITS

agues

1.33

geons

1.26

hops

1.23

 secrecy

1.22

igslist

1.21

endars

1.20

 impunity

1.19

 secretaries

1.19

ascus

1.19

rog

1.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.