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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.09

6:0.09

7:0.07

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

opian

-3.64

videos

-3.28

 CentOS

-2.91

Sense

-2.85

 podcasts

-2.82

espie

-2.77

 diapers

-2.63

tackle

-2.62

avis

-2.59

yle

-2.58

POSITIVE LOGITS

 Gren

3.01

 Bomb

2.67

Pal

2.67

 Chou

2.56

 Claim

2.46

HAM

2.41

Pic

2.41

 terror

2.39

 Bund

2.38

 Fernand

2.37

Activations Density 0.000%

No Known Activations

This feature has no known activations.