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

2:0.10

3:0.08

4:0.07

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

 Gutenberg

-1.46

rities

-1.45

 attractions

-1.40

kefeller

-1.40

 digit

-1.38

 Burr

-1.36

 plun

-1.34

illion

-1.33

psons

-1.29

inburgh

-1.26

POSITIVE LOGITS

Pwr

1.75

iasco

1.47

\\\\

1.47

Shy

1.47

lain

1.44

Mam

1.43

ayan

1.43

EStreamFrame

1.39

azes

1.36

hell

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.