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

0:0.09

1:0.08

2:0.08

3:0.08

4:0.06

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.11

11:0.04

Negative Logits

️

-1.71

 Pratt

-1.48

 Blumenthal

-1.28

 Clement

-1.26

 Milo

-1.25

 Innocent

-1.24

 Pablo

-1.21

 Gore

-1.20

 Fantastic

-1.16

 Caesar

-1.14

POSITIVE LOGITS

iversal

1.46

 relegation

1.41

advant

1.37

iffe

1.37

rul

1.36

ipedia

1.33

iciary

1.32

erenn

1.32

aceae

1.31

foundland

1.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.