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

2:0.08

3:0.07

4:0.08

5:0.07

6:0.09

7:0.08

8:0.09

9:0.07

10:0.09

11:0.07

Negative Logits

rique

-2.78

Putin

-2.75

ovych

-2.70

Mart

-2.65

Russia

-2.57

Xi

-2.57

Russ

-2.56

 Lumpur

-2.55

Pont

-2.55

arag

-2.53

POSITIVE LOGITS

 buckets

3.16

inburgh

3.07

 bucket

2.83

rawdownloadcloneembedreportprint

2.74

olean

2.67

 Fiesta

2.62

 pots

2.60

 Flavoring

2.54

 Equity

2.53

 Edinburgh

2.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.