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

1:0.07

2:0.08

3:0.09

4:0.06

5:0.08

6:0.10

7:0.08

8:0.07

9:0.09

10:0.07

11:0.08

Negative Logits

conn

-1.50

inational

-1.37

��

-1.36

 newcom

-1.32

�

-1.31

unct

-1.26

 Scarlet

-1.26

union

-1.24

foundland

-1.23

vertisement

-1.20

POSITIVE LOGITS

rency

1.48

 Canaver

1.43

cers

1.37

arial

1.36

 Sovereign

1.27

juries

1.26

vernment

1.25

itized

1.25

 glands

1.22

 "$:/

1.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.