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

1:0.07

2:0.08

3:0.07

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.09

Negative Logits

pip

-2.72

 Pagan

-2.64

Fa

-2.52

Characters

-2.41

 Dinosaur

-2.41

script

-2.39

PF

-2.36

Beer

-2.33

iments

-2.32

 drink

-2.31

POSITIVE LOGITS

 GOODMAN

3.03

 MacArthur

2.82

umbn

2.81

 Lynn

2.76

..................

2.75

kefeller

2.73

................

2.69

......

2.67

........................

2.65

↑

2.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.