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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

®,

-2.87

 labyrinth

-2.73

 fasc

-2.64

 Stretch

-2.57

 mathematical

-2.56

 polymorph

-2.53

 arrang

-2.52

enc

-2.50

 pave

-2.49

 subdivision

-2.46

POSITIVE LOGITS

izzle

2.79

ICE

2.67

ayne

2.67

inventoryQuantity

2.62

reb

2.62

assetsadobe

2.59

selage

2.58

tips

2.53

FG

2.52

Uber

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.