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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 festivals

-2.74

 storefront

-2.62

 venues

-2.62

 brands

-2.59

 establishments

-2.49

 retailers

-2.45

 Vehicle

-2.41

 cyclists

-2.32

 formats

-2.31

 stores

-2.31

POSITIVE LOGITS

inus

2.90

 Petraeus

2.82

gian

2.74

eus

2.71

覚醒

2.71

endez

2.69

Gry

2.68

 Picard

2.67

ulus

2.61

selage

2.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.