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

0:0.08

1:0.07

2:0.10

3:0.08

4:0.07

5:0.09

6:0.07

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 Unch

-1.55

 Exhibit

-1.44

represented

-1.36

Season

-1.32

leaning

-1.26

fell

-1.23

orus

-1.19

Actor

-1.17

 mainline

-1.17

rals

-1.16

POSITIVE LOGITS

wcsstore

1.62

�

1.51

urnal

1.51

orio

1.43

�

1.36

oshenko

1.34

PIN

1.33

soever

1.29

 msec

1.28

�

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.