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

1:0.08

2:0.08

3:0.10

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 Floor

-2.87

 Feature

-2.44

 Texture

-2.44

 Users

-2.43

 Tank

-2.42

Fl

-2.41

 Comment

-2.39

 Defenders

-2.38

 Usage

-2.37

DF

-2.33

POSITIVE LOGITS

peria

2.75

Romney

2.72

henko

2.71

oshenko

2.68

amacare

2.67

 vows

2.66

 resignation

2.63

Obama

2.56

Sov

2.52

 bride

2.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.