INDEX

Explanations

various uses of the word "form" and its derivatives indicating the creation or assembly of groups or entities

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

Head Attr Weights

0:0.03

1:0.03

2:0.03

3:0.03

4:0.05

5:0.03

6:0.04

7:0.04

8:0.02

9:0.10

10:0.02

11:0.52

Negative Logits

DIR

-2.05

 Editor

-1.98

bage

-1.96

FTWARE

-1.95

 Unleashed

-1.94

EngineDebug

-1.92

 Butcher

-1.89

 productivity

-1.88

ais

-1.88

--------------------------------------------------------

-1.87

POSITIVE LOGITS

 formed

3.45

 forming

3.15

 shape

3.12

 form

3.11

 forms

3.10

 formation

3.04

 formations

3.01

 bonds

2.88

 shapes

2.84

shape

2.81

Activations Density 0.058%

various uses of the word "form" and its derivatives indicating the creation or assembly of groups or entities

No Known Activations