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

0:0.09

1:0.09

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

!/

-1.24

orb

-1.24

liner

-1.21

mage

-1.21

define

-1.20

 thereof

-1.20

possibly

-1.17

wen

-1.17

unknown

-1.16

swer

-1.15

POSITIVE LOGITS

Ranked

1.60

女

1.50

ğ

1.50

▬

1.42

�

1.39

 Pengu

1.36

ogun

1.35

PID

1.33

isine

1.32

 Ranked

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.