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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.08

2:0.09

3:0.09

4:0.07

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

xit

-1.35

ulner

-1.31

missing

-1.31

ilibrium

-1.30

iae

-1.28

 Restore

-1.27

dll

-1.27

legates

-1.26

ithmetic

-1.25

angled

-1.24

POSITIVE LOGITS

.")

1.47

▬

1.46

ESPN

1.41

 showc

1.40

NYSE

1.38

 redes

1.36

 SPORTS

1.35

 therap

1.34

igans

1.34

��

1.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.