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

2:0.07

3:0.09

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

External

-3.15

Damage

-3.01

 Nico

-2.85

Duc

-2.67

Hat

-2.67

 Slash

-2.64

 Chevrolet

-2.63

 Thrust

-2.63

Plugin

-2.59

 Adidas

-2.58

POSITIVE LOGITS

 lantern

3.47

gins

3.20

 volunt

2.95

dayName

2.87

 warr

2.71

 skyline

2.69

 scen

2.64

arden

2.63

orest

2.61

vill

2.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.