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

0:0.07

1:0.07

2:0.08

3:0.10

4:0.09

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.09

Negative Logits

Wyr

-1.79

atel

-1.78

 Salon

-1.76

 Grande

-1.67

NS

-1.64

anse

-1.56

 pageant

-1.53

 Anthrop

-1.53

Tan

-1.51

illet

-1.51

POSITIVE LOGITS

helps

1.85

ウス

1.71

"""

1.70

 motiv

1.70

 aids

1.68

-'

1.68

\"

1.65

lator

1.63

�

1.60

 treasurer

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.