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

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.10

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

 Maced

-3.09

Neo

-2.75

ulic

-2.69

 Euph

-2.68

[&

-2.65

Maps

-2.63

 Cannabis

-2.59

arus

-2.59

Sche

-2.56

 Ukrain

-2.56

POSITIVE LOGITS

thouse

2.92

pton

2.77

isexual

2.77

 Tiffany

2.70

 Betty

2.69

 divest

2.62

solid

2.59

 Dunn

2.58

 tender

2.54

elson

2.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.