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

1:0.07

2:0.09

3:0.09

4:0.08

5:0.09

6:0.07

7:0.07

8:0.06

9:0.09

10:0.10

11:0.08

Negative Logits

DT

-1.55

izz

-1.47

 prov

-1.37

 Burr

-1.35

 politic

-1.34

block

-1.29

enda

-1.29

redo

-1.28

abus

-1.27

OTUS

-1.26

POSITIVE LOGITS

staking

1.97

adders

1.71

inav

1.62

phies

1.61

rals

1.57

sembly

1.54

 nets

1.53

lean

1.51

ESA

1.50

NESS

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.