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

1:0.09

2:0.09

3:0.07

4:0.08

5:0.09

6:0.09

7:0.09

8:0.06

9:0.07

10:0.07

11:0.07

Negative Logits

Ara

-1.38

 Cosponsors

-1.34

Ya

-1.31

eatured

-1.29

 HTTPS

-1.22

 Bened

-1.21

Wa

-1.19

 Digest

-1.19

Fat

-1.18

ur

-1.17

POSITIVE LOGITS

aukee

1.52

norm

1.48

wagen

1.41

acci

1.39

onent

1.38

jury

1.35

lins

1.35

Ont

1.35

estate

1.33

iston

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.