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

2:0.08

3:0.08

4:0.07

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

 Telegram

-3.28

 Radar

-2.97

ola

-2.69

ofi

-2.67

 Patent

-2.65

 cryptography

-2.60

Rad

-2.53

ati

-2.52

 Ring

-2.50

 Rost

-2.49

POSITIVE LOGITS

Tes

3.10

quickShipAvailable

2.79

inventoryQuantity

2.76

 Clicker

2.75

urches

2.73

 裏覚醒

2.65

pmwiki

2.62

ustain

2.59

EngineDebug

2.59

 Chloe

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.