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

3:0.09

4:0.09

5:0.07

6:0.06

7:0.08

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

 electronically

-2.74

graded

-2.69

 composite

-2.69

 Destiny

-2.58

UA

-2.56

 Unity

-2.52

 archive

-2.49

 distinctive

-2.43

 Valiant

-2.43

 territory

-2.39

POSITIVE LOGITS

lad

2.91

iolet

2.72

Indust

2.70

daq

2.62

lace

2.60

░

2.59

laus

2.56

 Meow

2.54

 Lank

2.54

ccording

2.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.