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

1:0.07

2:0.09

3:0.06

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

 smugg

-2.89

 voyage

-2.89

 disembark

-2.82

 Alone

-2.71

ctuary

-2.65

uta

-2.62

archives

-2.61

 yacht

-2.58

quished

-2.55

aja

-2.52

POSITIVE LOGITS

olson

2.77

baugh

2.63

 guts

2.56

ADVERTISEMENT

2.49

 Lerner

2.41

 Foley

2.37

 recognizable

2.27

 BALL

2.27

oller

2.24

 Burnett

2.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.