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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.10

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.06

10:0.09

11:0.08

Negative Logits

SPONSORED

-1.72

�

-1.27

 rival

-1.26

ynes

-1.26

thood

-1.25

ifer

-1.24

rising

-1.23

 slic

-1.21

ioned

-1.20

guards

-1.19

POSITIVE LOGITS

querade

1.57

 Ange

1.54

creen

1.54

EStream

1.53

ahime

1.48

lain

1.44

 Lumpur

1.43

��

1.42

liga

1.36

_>

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.