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

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

 recognise

-2.75

 acknowledgement

-2.73

 recogn

-2.71

 recognised

-2.69

ç

-2.61

 Jinn

-2.59

 offence

-2.57

 centre

-2.48

 Islam

-2.43

 Beckham

-2.37

POSITIVE LOGITS

ducers

3.04

 herds

2.92

dies

2.64

ufact

2.59

ugi

2.49

 herd

2.47

Disney

2.43

 chili

2.38

urdue

2.37

Company

2.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.