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

0:0.09

1:0.07

2:0.07

3:0.10

4:0.09

5:0.08

6:0.07

7:0.07

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

 Role

-2.99

 Tube

-2.98

 Adventures

-2.83

 Seat

-2.79

EE

-2.76

 Benefits

-2.70

 Contributions

-2.66

 Component

-2.60

 Ride

-2.59

 Norton

-2.57

POSITIVE LOGITS

 prom

2.56

 millisec

2.50

ethyst

2.49

icably

2.47

skip

2.47

ouble

2.44

sync

2.43

etsk

2.39

recy

2.39

 pessim

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.