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

3:0.07

4:0.07

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.09

Negative Logits

swer

-1.61

ifier

-1.47

Nom

-1.46

epad

-1.43

 Rover

-1.34

 Nigel

-1.31

ainer

-1.30

arette

-1.29

Elect

-1.29

icity

-1.29

POSITIVE LOGITS

Initialized

1.86

soType

1.54

initialized

1.53

��

1.51

dimension

1.47

龍喚士

1.43

oha

1.42

 accountable

1.41

 equitable

1.39

galitarian

1.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.