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

3:0.07

4:0.08

5:0.08

6:0.07

7:0.10

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

MET

-2.70

 fanbase

-2.67

AUD

-2.50

 Collider

-2.45

ODY

-2.45

 Syndicate

-2.42

 Media

-2.39

imet

-2.37

Met

-2.31

MI

-2.27

POSITIVE LOGITS

blank

2.61

 Sith

2.59

̶

2.58

eus

2.54

ansk

2.53

 droid

2.50

hillary

2.49

Philipp

2.48

sburg

2.47

�

2.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.