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

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.07

4:0.07

5:0.07

6:0.09

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

 Grateful

-1.52

 Vict

-1.49

Kid

-1.41

FY

-1.40

Zip

-1.38

Mot

-1.36

 Wrestle

-1.34

ikuman

-1.32

Wave

-1.32

Fug

-1.31

POSITIVE LOGITS

 Carney

1.40

ilic

1.35

ield

1.30

 broadly

1.24

├

1.24

 mainly

1.24

}}

1.24

aic

1.22

م

1.21

 campaigners

1.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.