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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.09

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 Glac

-1.49

 accumulating

-1.48

 defect

-1.45

 polymorph

-1.45

 landsl

-1.32

 digit

-1.32

 fractions

-1.32

 accumulation

-1.32

omal

-1.31

 settlers

-1.30

POSITIVE LOGITS

 guiName

1.56

═

1.52

azon

1.43

——

1.42

..............

1.41

 Bastard

1.39

▬

1.39

Smart

1.37

advertising

1.36

 Hogan

1.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.