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

1:0.13

2:0.08

3:0.06

4:0.08

5:0.09

6:0.07

7:0.06

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Unlimited

-2.00

 Dimensions

-1.73

 Tennis

-1.69

 Sheldon

-1.64

HOT

-1.57

 Sports

-1.54

 Round

-1.53

 Showdown

-1.53

 Sens

-1.52

 Circus

-1.51

POSITIVE LOGITS

ivan

2.46

2.21

arak

1.95

assad

1.94

enary

1.92

anamo

1.79

mort

1.77

anan

1.77

tro

1.76

 rede

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.