INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

3:0.07

4:0.10

5:0.10

6:0.07

7:0.08

8:0.07

9:0.06

10:0.09

11:0.07

Negative Logits

PHOTOS

-1.27

 payroll

-1.20

 paycheck

-1.19

 sleeves

-1.17

 generation

-1.12

 quint

-1.11

 cancers

-1.11

 bandwagon

-1.10

 darn

-1.09

MORE

-1.09

POSITIVE LOGITS

 scrut

1.63

 acknow

1.42

=-=-

1.39

cknow

1.39

irit

1.33

eer

1.31

eers

1.31

awa

1.30

═

1.29

 nomine

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.