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

0:0.09

1:0.09

2:0.08

3:0.08

4:0.08

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

Hai

-2.75

 programmes

-2.71

sein

-2.71

 Rahman

-2.70

 Hussain

-2.64

 Indonesia

-2.61

hani

-2.58

hao

-2.52

zee

-2.48

Wan

-2.47

POSITIVE LOGITS

 bystanders

2.76

 Lane

2.71

 Verizon

2.70

DMV

2.67

 Defendants

2.63

alon

2.50

enfranch

2.41

 Lafayette

2.31

oros

2.30

 Trooper

2.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.