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

0:0.09

1:0.08

2:0.09

3:0.08

4:0.07

5:0.08

6:0.07

7:0.09

8:0.06

9:0.08

10:0.07

11:0.08

Negative Logits

 excludes

-1.73

 Dictionary

-1.66

 counterfe

-1.51

owitz

-1.51

 thinner

-1.49

 protects

-1.48

 thicker

-1.45

 Unlimited

-1.44

 Armageddon

-1.44

 counterfeit

-1.43

POSITIVE LOGITS

accompanied

2.02

psey

1.85

sit

1.74

plets

1.73

monton

1.72

glomer

1.72

vill

1.70

spection

1.63

GROUP

1.63

 showc

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.