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

1:0.07

2:0.09

3:0.07

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

CRE

-3.08

 ANGEL

-3.05

 Dear

-2.85

 Clown

-2.81

 Kelley

-2.79

Cer

-2.75

Lan

-2.68

 Boll

-2.67

 Hobby

-2.65

 Sins

-2.53

POSITIVE LOGITS

hut

2.80

 oats

2.80

nav

2.73

 magnification

2.71

 importing

2.61

avascript

2.60

 ration

2.54

 compass

2.51

 Nile

2.48

nep

2.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.