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

1:0.10

2:0.09

3:0.07

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Roundup

-3.00

 Kaplan

-3.00

GMO

-2.80

 Register

-2.78

 Olympia

-2.77

 ARTICLE

-2.76

ruct

-2.75

 Chapters

-2.64

姫

-2.63

chwitz

-2.60

POSITIVE LOGITS

 subconscious

2.83

 parting

2.74

 disapp

2.69

 fade

2.60

 jarring

2.58

 incons

2.53

 commute

2.53

 commuting

2.53

 anecd

2.52

 uncommon

2.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.