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

2:0.07

3:0.08

4:0.07

5:0.07

6:0.08

7:0.09

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

 Schwarz

-2.82

 Sloan

-2.71

 Loft

-2.71

��

-2.70

 neut

-2.68

 enriched

-2.67

 Mull

-2.66

NH

-2.64

gem

-2.64

reflect

-2.57

POSITIVE LOGITS

opsis

3.35

├

2.83

 Rodrigo

2.81

 Venezuelan

2.79

 Sacramento

2.73

 Paragu

2.72

ê

2.66

 Manila

2.64

 Colombia

2.64

quished

2.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.