INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.06

1:0.04

2:0.10

3:0.08

4:0.08

5:0.09

6:0.07

7:0.10

8:0.07

9:0.10

10:0.08

11:0.08

Negative Logits

 quantity

-1.33

ilight

-1.28

 Keane

-1.27

 Steele

-1.22

 Lamp

-1.22

 RELE

-1.21

dun

-1.21

aff

-1.20

ded

-1.19

)].

-1.19

POSITIVE LOGITS

omo

1.59

cas

1.52

odan

1.48

 WATCHED

1.42

crew

1.42

nexus

1.39

RG

1.39

Snake

1.34

emale

1.30

Rocket

1.29

Activations Density 0.000%

No Known Activations

This feature has no known activations.