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

1:0.10

2:0.08

3:0.07

4:0.08

5:0.07

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Astros

-2.75

 coughing

-2.73

 Hamp

-2.63

 agriculture

-2.53

 Hein

-2.53

 Hades

-2.49

enges

-2.46

FG

-2.45

 artillery

-2.38

 Agriculture

-2.37

POSITIVE LOGITS

-+-+

2.76

 moder

2.70

PLIC

2.69

 "$:/

2.65

omo

2.56

 supra

2.52

ortal

2.51

 Moder

2.51

"!

2.45

 Clockwork

2.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.