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

0:0.10

1:0.12

2:0.07

3:0.07

4:0.08

5:0.08

6:0.06

7:0.08

8:0.07

9:0.06

10:0.08

11:0.08

Negative Logits

eways

-1.92

Reply

-1.74

 hers

-1.73

 unimagin

-1.71

EngineDebug

-1.66

,,

-1.60

——

-1.58

stration

-1.49

 onward

-1.47

 unint

-1.46

POSITIVE LOGITS

osate

1.81

ofi

1.80

kid

1.78

gate

1.75

 Fenrir

1.71

 Slip

1.70

regor

1.69

isite

1.68

otype

1.65

DragonMagazine

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.