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

1:0.09

2:0.09

3:0.08

4:0.08

5:0.09

6:0.07

7:0.08

8:0.07

9:0.07

10:0.09

11:0.07

Negative Logits

finished

-2.75

emetery

-2.73

erest

-2.55

hett

-2.43

nyder

-2.41

cake

-2.40

uel

-2.36

iami

-2.34

onite

-2.33

 foreclosure

-2.32

POSITIVE LOGITS

 exerc

3.02

 Exercise

2.90

 Advocate

2.75

 Scorp

2.68

RSS

2.66

 Nasa

2.51

Scroll

2.50

 Constable

2.48

SPONSORED

2.46

SPD

2.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.