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

0:0.08

1:0.07

2:0.09

3:0.09

4:0.09

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

yip

-2.78

uggest

-2.77

uterte

-2.63

utan

-2.58

utra

-2.53

Rogue

-2.50

Bro

-2.46

roid

-2.46

人

-2.43

hent

-2.42

POSITIVE LOGITS

���

2.83

 workload

2.52

 trucks

2.47

 Baseball

2.45

 Vehicles

2.44

 polling

2.44

 Clarks

2.44

illery

2.38

 chemotherapy

2.35

 COURT

2.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.