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

1:0.07

2:0.07

3:0.07

4:0.09

5:0.08

6:0.08

7:0.09

8:0.09

9:0.09

10:0.08

11:0.07

Negative Logits

Kag

-3.14

 aides

-2.92

Kou

-2.90

 Fischer

-2.59

 photoc

-2.59

�

-2.58

 mentally

-2.54

 kinderg

-2.50

''

-2.50

 pengu

-2.49

POSITIVE LOGITS

ModLoader

2.89

href

2.83

ABV

2.78

Scope

2.78

rama

2.69

venture

2.68

 Nemesis

2.68

 Ventures

2.67

 explorer

2.67

Theme

2.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.