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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.07

3:0.08

4:0.09

5:0.07

6:0.07

7:0.09

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 Archie

-2.63

Ble

-2.62

 nerves

-2.56

 Lanc

-2.54

 Comics

-2.50

 fandom

-2.46

 Muscle

-2.32

 Kyle

-2.30

 Griffin

-2.30

dale

-2.28

POSITIVE LOGITS

furt

2.83

2.81

discrimination

2.65

ctors

2.58

pas

2.58

beit

2.57

ciation

2.56

cussion

2.50

Employ

2.48

Address

2.46

Activations Density 0.000%

No Known Activations

This feature has no known activations.