INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.06

2:0.08

3:0.06

4:0.08

5:0.08

6:0.09

7:0.09

8:0.10

9:0.07

10:0.08

11:0.07

Negative Logits

EPA

-1.44

 WARN

-1.44

ghai

-1.40

◼

-1.39

 Cosponsors

-1.25

zed

-1.23

sted

-1.22

 ment

-1.21

 sheep

-1.20

'';

-1.19

POSITIVE LOGITS

 resume

1.64

mania

1.57

lished

1.42

 Franch

1.39

agame

1.36

 Crescent

1.35

キ

1.33

 Colon

1.33

emate

1.31

ioxide

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.