INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.06

2:0.08

3:0.09

4:0.08

5:0.09

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.09

Negative Logits

 simulate

-1.74

 simplified

-1.66

 interpol

-1.62

kef

-1.61

 subdiv

-1.58

 accelerated

-1.53

 volunt

-1.51

 concentrated

-1.48

 simulator

-1.48

 visualization

-1.47

POSITIVE LOGITS

Ct

1.79

Jew

1.78

endif

1.70

Armor

1.66

AFP

1.58

Dust

1.56

Eva

1.55

Cry

1.55

Jac

1.51

Matt

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.