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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.08

5:0.08

6:0.09

7:0.08

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

NetMessage

-1.48

USH

-1.38

 saving

-1.38

eatures

-1.34

erous

-1.27

ND

-1.23

eval

-1.22

 Saving

-1.21

.*

-1.21

 appealing

-1.19

POSITIVE LOGITS

cised

1.76

ocese

1.64

apist

1.58

osphere

1.54

 Franç

1.50

rette

1.48

ecast

1.46

 encyclopedia

1.42

aeda

1.42

nesota

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.