INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.10

1:0.07

2:0.08

3:0.07

4:0.06

5:0.07

6:0.08

7:0.10

8:0.06

9:0.07

10:0.10

11:0.09

Negative Logits

taboola

-2.34

KEY

-2.14

-2.11

 averages

-2.11

 offsets

-1.95

 barrels

-1.93

 trillions

-1.90

TD

-1.89

dx

-1.89

TX

-1.88

POSITIVE LOGITS

 Flesh

2.49

 Absent

2.39

 Grave

2.30

 Mixed

2.30

 Shelter

2.23

 Masquerade

2.22

 Silent

2.22

 Clouds

2.22

 Sleeping

2.21

Sau

2.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.