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

1:0.09

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.06

Negative Logits

 Blockchain

-2.93

ETA

-2.73

 Barclays

-2.68

 Procedure

-2.67

vari

-2.67

cko

-2.64

 Carlo

-2.62

 repud

-2.59

istor

-2.54

hash

-2.53

POSITIVE LOGITS

 lone

2.81

 airst

2.64

 livest

2.58

psey

2.50

 canoe

2.47

Hig

2.47

 humid

2.46

 Lone

2.41

 larg

2.40

 gifts

2.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.