INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.1.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

0:0.07

1:0.08

2:0.09

3:0.05

4:0.09

5:0.07

6:0.08

7:0.10

8:0.06

9:0.06

10:0.10

11:0.09

Negative Logits

 modelling

-1.39

 races

-1.30

 Johannes

-1.29

ysics

-1.25

ozo

-1.24

WM

-1.23

icle

-1.23

 metre

-1.22

rified

-1.20

 Celt

-1.20

POSITIVE LOGITS

Interstitial

1.82

1.53

 counterproductive

1.50

entimes

1.49

 egregious

1.37

adan

1.36

 coercive

1.33

 inconvenient

1.26

 repressive

1.25

 nonexistent

1.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.