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

1:0.08

2:0.07

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

 love

-2.84

 Patron

-2.77

 faithful

-2.71

Cou

-2.67

 rapport

-2.66

 knit

-2.62

 groove

-2.61

 familial

-2.61

tie

-2.59

 Lord

-2.57

POSITIVE LOGITS

HUD

3.47

assium

3.35

halla

2.97

ysis

2.87

haar

2.81

 prosec

2.80

WithNo

2.73

 裏覚醒

2.71

successfully

2.70

emp

2.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.