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

4:0.07

5:0.08

6:0.08

7:0.09

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

神

-2.97

VID

-2.87

ヘ

-2.74

Num

-2.65

icipated

-2.60

soDeliveryDate

-2.56

 thoughtful

-2.56

MA

-2.48

Vote

-2.47

UCT

-2.46

POSITIVE LOGITS

Anonymous

2.78

Hof

2.64

','

2.61

Leaks

2.61

',"

2.60

ewitness

2.60

eru

2.60

 neighbouring

2.50

 fishes

2.50

 autonom

2.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.