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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.07

5:0.07

6:0.09

7:0.10

8:0.08

9:0.09

10:0.07

11:0.08

Negative Logits

 clam

-2.62

orpor

-2.50

 shareholders

-2.44

 Lerner

-2.43

 Grateful

-2.42

Publisher

-2.31

liam

-2.29

ongevity

-2.25

 Lauder

-2.24

 lawy

-2.23

POSITIVE LOGITS

cffffcc

2.60

UC

2.46

threat

2.43

camp

2.39

PTS

2.38

Rank

2.34

racuse

2.31

BILITIES

2.30

Miss

2.30

isSpecialOrderable

2.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.