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

3:0.08

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 commute

-3.22

 commuting

-2.92

 taxis

-2.65

 taxi

-2.46

ict

-2.45

idth

-2.44

 preference

-2.44

idget

-2.42

 Dublin

-2.41

arded

-2.41

POSITIVE LOGITS

 Maker

2.50

 Crusade

2.46

blow

2.45

 Demonic

2.45

 Blow

2.38

 TAMADRA

2.38

{*

2.35

Spirit

2.33

 Predator

2.31

 Arms

2.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.