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

0:0.09

1:0.07

2:0.07

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.07

Negative Logits

upt

-2.89

dden

-2.87

inx

-2.71

leans

-2.69

ento

-2.65

oof

-2.56

 Lonely

-2.53

yip

-2.50

weak

-2.50

addons

-2.44

POSITIVE LOGITS

 Forensic

3.14

 Proceedings

3.01

 glac

2.82

 Mueller

2.79

 Mathematics

2.71

 Gret

2.50

 Stras

2.48

 NASA

2.48

 forensic

2.47

 Tillerson

2.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.