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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.09

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.06

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

urrection

-1.35

mens

-1.29

-1.26

upiter

-1.23

ymph

-1.22

vernment

-1.20

ordinary

-1.18

Eva

-1.16

 Tens

-1.15

 fold

-1.14

POSITIVE LOGITS

 advoc

1.89

anwhile

1.72

 mathemat

1.63

 destro

1.53

 distingu

1.46

 blat

1.45

 assum

1.45

 advis

1.42

 Lack

1.40

 proble

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.