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

1:0.08

2:0.09

3:0.08

4:0.08

5:0.07

6:0.09

7:0.08

8:0.06

9:0.08

10:0.07

11:0.09

Negative Logits

Torrent

-1.28

vo

-1.25

 sshd

-1.22

 Oath

-1.20

 FOIA

-1.18

 Plymouth

-1.17

Grant

-1.15

spec

-1.15

ributed

-1.15

 Torrent

-1.13

POSITIVE LOGITS

itiveness

1.48

interstitial

1.45

hua

1.35

 Nieto

1.34

 CEOs

1.33

atron

1.21

nyder

1.20

 Incarn

1.20

inki

1.19

ITIES

1.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.