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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.09

6:0.07

7:0.08

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

xtap

-2.70

raq

-2.69

 recomb

-2.55

itia

-2.55

��

-2.54

acet

-2.44

cum

-2.43

 recol

-2.40

ウス

-2.38

 conver

-2.37

POSITIVE LOGITS

 Nurse

3.14

 Slater

3.10

 Nerd

2.96

 Nationwide

2.66

 Expend

2.64

 Volunte

2.63

 Deaths

2.62

 Murd

2.56

 Survivors

2.55

 Sick

2.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.