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

1:0.08

2:0.09

3:0.06

4:0.09

5:0.07

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.07

Negative Logits

ezvous

-1.60

Buzz

-1.51

RON

-1.46

oint

-1.44

ylan

-1.42

VID

-1.42

rued

-1.42

ultane

-1.41

gets

-1.41

inburgh

-1.40

POSITIVE LOGITS

��

1.64

 Antar

1.61

CoC

1.54

���

1.47

 Firearms

1.47

 Ninth

1.45

 corrid

1.43

 Pediatrics

1.37

rul

1.35

 outlawed

1.35

Activations Density 0.000%

No Known Activations

This feature has no known activations.