INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.06

1:0.09

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

TPP

-2.98

 contrace

-2.75

osition

-2.75

Policy

-2.73

irtual

-2.69

obos

-2.69

ocy

-2.59

 Spart

-2.50

camp

-2.49

CDC

-2.47

POSITIVE LOGITS

Jah

2.75

 Thomson

2.46

 partName

2.42

nem

2.40

 Rahman

2.40

 Dame

2.40

 Myst

2.37

FIN

2.34

Bro

2.30

Fin

2.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.