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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.07

5:0.07

6:0.09

7:0.09

8:0.08

9:0.10

10:0.08

11:0.07

Negative Logits

forest

-1.28

️

-1.27

 homelessness

-1.20

 disproportion

-1.19

ibly

-1.17

blogs

-1.17

vic

-1.15

rists

-1.14

istan

-1.11

Case

-1.10

POSITIVE LOGITS

acket

1.59

atari

1.48

mosp

1.45

urus

1.33

 Burst

1.29

alus

1.26

onse

1.25

 Cooldown

1.22

魔

1.21

urion

1.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.