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

1:0.08

2:0.07

3:0.08

4:0.07

5:0.08

6:0.07

7:0.10

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Rebellion

-3.43

 Rebell

-2.79

Soy

-2.74

 Indra

-2.67

qua

-2.59

天

-2.58

Wan

-2.55

..............

-2.50

Iv

-2.45

 Roku

-2.45

POSITIVE LOGITS

 documenting

2.83

ERAL

2.58

 detailing

2.45

 accompl

2.42

00200000

2.42

 calming

2.30

 locating

2.28

 fixing

2.27

 watering

2.27

 docking

2.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.