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

0:0.06

1:0.06

2:0.09

3:0.07

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.09

11:0.09

Negative Logits

CLOSE

-2.01

 Flavoring

-1.86

 viewpoint

-1.56

 SetFontSize

-1.53

�

-1.43

POV

-1.37

 Ghostbusters

-1.36

 Position

-1.35

advertising

-1.34

Role

-1.34

POSITIVE LOGITS

ieth

1.72

 pled

1.67

inguished

1.63

ilant

1.61

ryn

1.57

hall

1.55

vo

1.53

alse

1.52

stre

1.51

adian

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.