INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.07

1:0.08

2:0.10

3:0.08

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 monop

-2.97

 Liberties

-2.97

 unbeliev

-2.69

 Pigs

-2.68

 Pill

-2.58

uphem

-2.56

inet

-2.55

 Friedman

-2.52

Fib

-2.50

 Dise

-2.48

POSITIVE LOGITS

�

2.99

 Charleston

2.93

afort

2.88

 Clippers

2.65

angered

2.62

 cornerback

2.46

 Borderlands

2.44

 offseason

2.43

acio

2.39

cheon

2.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.