INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.09

8:0.08

9:0.10

10:0.07

11:0.07

Negative Logits

ateurs

-3.04

ゴン

-2.95

�

-2.60

 Paint

-2.58

 Nike

-2.52

adobe

-2.52

 Bounce

-2.49

 monop

-2.48

代

-2.46

 neglig

-2.45

POSITIVE LOGITS

*)

2.72

SPONSORED

2.56

…]

2.39

 delim

2.36

Si

2.36

 Manit

2.32

Plot

2.26

vation

2.22

]'

2.17

 benches

2.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.