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

1:0.09

2:0.07

3:0.09

4:0.09

5:0.09

6:0.07

7:0.06

8:0.07

9:0.07

10:0.07

11:0.10

Negative Logits

 tourists

-3.21

 flyers

-2.67

 shove

-2.58

 doorstep

-2.56

 passers

-2.56

 screenings

-2.53

 leaflets

-2.49

 shoppers

-2.46

 bystanders

-2.45

 scissors

-2.44

POSITIVE LOGITS

ivated

2.83

�

2.79

Â

2.74

�

2.71

NAS

2.70

ヴァ

2.69

2.67

ortium

2.67

ć

2.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.