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

0:0.09

1:0.08

2:0.08

3:0.09

4:0.07

5:0.08

6:0.07

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

isSpecialOrderable

-1.81

 CrossRef

-1.77

,,,,

-1.71

 Walters

-1.68

 Citation

-1.63

selves

-1.61

 Household

-1.60

BuyableInstoreAndOnline

-1.57

 Lower

-1.56

sters

-1.56

POSITIVE LOGITS

2.51

aut

2.11

 isolation

1.83

覚醒

1.83

 sailor

1.82

ym

1.81

 axis

1.79

idon

1.78

essim

1.77

axis

1.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.