INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.09

7:0.08

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

SAT

-3.58

onge

-3.24

 Wald

-3.07

jong

-2.96

SUN

-2.88

NK

-2.83

 Nord

-2.81

 Niet

-2.78

Cong

-2.74

�

-2.73

POSITIVE LOGITS

 Harris

2.71

 Amir

2.69

 Cyborg

2.56

Harris

2.52

/>

2.46

DC

2.45

Os

2.38

ush

2.38

 Floyd

2.31

 Hogan

2.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.