INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

3:0.07

4:0.07

5:0.07

6:0.08

7:0.08

8:0.09

9:0.09

10:0.07

11:0.08

Negative Logits

breaker

-1.33

Sleep

-1.30

tro

-1.30

vict

-1.26

×

-1.25

bread

-1.23

iband

-1.21

alys

-1.20

Brother

-1.20

Background

-1.19

POSITIVE LOGITS

argon

1.52

vironment

1.50

chnology

1.44

 archives

1.44

��

1.37

PLIED

1.36

 nonprofits

1.36

��

1.34

 Intelligent

1.28

 payroll

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.