INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.08

2:0.07

3:0.09

4:0.09

5:0.07

6:0.06

7:0.08

8:0.10

9:0.07

10:0.08

11:0.07

Negative Logits

[/

-1.51

rb

-1.50

{}

-1.49

seless

-1.46

sing

-1.45

ss

-1.42

nt

-1.39

ses

-1.37

 lack

-1.34

orks

-1.33

POSITIVE LOGITS

folios

1.42

adena

1.41

mares

1.40

eers

1.38

achus

1.37

 apostle

1.37

\\\\\\\\

1.36

LOD

1.35

uten

1.34

DAQ

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.