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

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

netflix

-2.86

ーク

-2.84

 Currency

-2.77

BuyableInstoreAndOnline

-2.67

currency

-2.62

buquerque

-2.61

 piracy

-2.56

 pand

-2.54

 currencies

-2.51

rencies

-2.49

POSITIVE LOGITS

eous

2.48

________________________

2.41

Uk

2.35

________________________________

2.32

hod

2.32

 Gareth

2.31

GAN

2.25

hawk

2.25

ourt

2.23

leigh

2.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.