INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.06

1:0.06

2:0.14

3:0.07

4:0.07

5:0.12

6:0.05

7:0.06

8:0.07

9:0.08

10:0.10

11:0.06

Negative Logits

azeera

-1.74

istries

-1.49

DAQ

-1.47

iens

-1.34

ゴン

-1.33

odon

-1.29

INESS

-1.27

utra

-1.25

erala

-1.24

ibles

-1.24

POSITIVE LOGITS

cknowled

1.17

ritical

1.14

***

1.12

 conditioned

1.09

 Celest

1.06

���

1.04

 SOME

1.04

 disgruntled

1.04

bent

1.03

 Ange

1.02

Activations Density 0.000%

No Known Activations

This feature has no known activations.