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

1:0.06

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.08

10:0.09

11:0.10

Negative Logits

tnc

-1.57

 literacy

-1.49

 couples

-1.46

 helium

-1.44

 sanity

-1.43

Ng

-1.41

chuk

-1.39

 relativity

-1.38

 toggle

-1.32

Geh

-1.30

POSITIVE LOGITS

Downloadha

1.93

BALL

1.60

 respectively

1.51

milo

1.51

 NEWS

1.48

 Prayer

1.44

osponsors

1.43

mails

1.39

awar

1.38

 Apprentice

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.