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

2:0.08

3:0.08

4:0.09

5:0.07

6:0.08

7:0.07

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

 herald

-2.41

 Influ

-2.31

 consistently

-2.31

 jewelry

-2.29

 accessory

-2.28

flu

-2.23

ograph

-2.21

 firmware

-2.18

†

-2.15

�

-2.15

POSITIVE LOGITS

ESA

3.08

Stretch

2.69

Topics

2.67

bryce

2.64

Future

2.56

Chair

2.52

livious

2.47

TPP

2.46

razil

2.45

cair

2.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.