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

1:0.08

2:0.08

3:0.08

4:0.07

5:0.08

6:0.07

7:0.07

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

raft

-1.46

 Resist

-1.41

rowth

-1.40

uilding

-1.30

ify

-1.28

strength

-1.27

root

-1.26

oots

-1.23

 Relief

-1.22

une

-1.21

POSITIVE LOGITS

AMS

1.61

 pseudonym

1.57

xual

1.54

ּ

1.48

 newsp

1.48

 elig

1.46

 cents

1.41

udeau

1.40

 depreciation

1.39

quickShipAvailable

1.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.