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

0:0.08

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.07

11:0.07

Negative Logits

;;;;;;;;;;;;

-3.11

ozyg

-2.81

 Animation

-2.49

 Monsters

-2.48

ipel

-2.48

reditary

-2.45

xon

-2.44

 buffs

-2.42

;;;;;;;;

-2.37

adjusted

-2.35

POSITIVE LOGITS

 Sang

2.73

sin

2.70

inn

2.56

 Baghd

2.51

 begg

2.46

 solitary

2.41

abus

2.40

 seiz

2.39

pil

2.37

 spokes

2.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.