INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.08

1:0.08

2:0.07

3:0.09

4:0.08

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

––

-3.23

�

-3.18

 Caucus

-3.05

 SNAP

-3.00

SPONSORED

-2.75

-->

-2.72

 decl

-2.65

photos

-2.63

 DACA

-2.62

Democrats

-2.60

POSITIVE LOGITS

rique

2.57

Mit

2.49

eal

2.44

 Merlin

2.41

 Notting

2.39

grave

2.37

iley

2.32

 remed

2.29

 Glas

2.29

 Trafford

2.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.