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

0:0.09

1:0.09

2:0.09

3:0.08

4:0.08

5:0.07

6:0.07

7:0.07

8:0.09

9:0.08

10:0.08

11:0.07

Negative Logits

akespe

-1.47

 marqu

-1.43

atin

-1.38

 alters

-1.36

verts

-1.35

 nipples

-1.34

 Lovecraft

-1.33

 indecent

-1.32

 modelling

-1.30

 scrolls

-1.30

POSITIVE LOGITS

 Opposition

1.49

ometown

1.47

 Infrastructure

1.47

 Communities

1.39

ARGET

1.34

 Ways

1.31

 Ahead

1.30

 Shutdown

1.29

entimes

1.28

 guiIcon

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.