INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

3:0.09

4:0.06

5:0.09

6:0.07

7:0.09

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

illa

-2.55

chin

-2.34

icle

-2.29

throp

-2.25

oho

-2.22

Strike

-2.19

 childbirth

-2.18

hew

-2.15

BB

-2.15

rite

-2.14

POSITIVE LOGITS

[*]

2.91

$_

2.89

«

2.81

EMS

2.51

«

2.48

 Cunningham

2.47

 Kuwait

2.45

 reversible

2.44

 Kurd

2.41

»

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.