INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.06

2:0.08

3:0.11

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

sd

-1.80

 Percent

-1.64

plet

-1.53

plus

-1.52

 Calculator

-1.50

 Etsy

-1.48

 PAGE

-1.46

mint

-1.44

 Coinbase

-1.41

ertation

-1.40

POSITIVE LOGITS

 solitude

1.74

Hope

1.73

 horizont

1.68

emn

1.66

 impunity

1.64

 resumed

1.62

UTERS

1.61

 happier

1.55

Domin

1.54

 quieter

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.