INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

2:0.06

3:0.08

4:0.09

5:0.09

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

cies

-3.02

 Bees

-2.89

risome

-2.86

ihad

-2.68

catentry

-2.65

icides

-2.58

iotic

-2.57

otin

-2.55

awks

-2.54

locks

-2.52

POSITIVE LOGITS

Mayor

2.78

 banquet

2.43

 pedest

2.42

 Lumpur

2.36

 Restaurant

2.34

 supper

2.33

 hospitality

2.32

 Harbor

2.31

 mayor

2.28

 restaur

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.