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

0:0.06

1:0.07

2:0.09

3:0.06

4:0.09

5:0.08

6:0.08

7:0.09

8:0.09

9:0.09

10:0.08

11:0.08

Negative Logits

Null

-1.36

sole

-1.33

bearing

-1.33

 comma

-1.33

idable

-1.32

arer

-1.30

states

-1.27

Minor

-1.26

Against

-1.24

ansas

-1.21

POSITIVE LOGITS

giene

1.49

ulz

1.37

 ageing

1.37

enegger

1.36

 Extend

1.33

 neighbourhood

1.33

itsch

1.31

bsite

1.31

 Refresh

1.30

(£

1.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.