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

4:0.06

5:0.09

6:0.09

7:0.07

8:0.08

9:0.09

10:0.07

11:0.09

Negative Logits

 constitu

-2.03

 Flavoring

-1.92

 Belief

-1.86

 diapers

-1.80

thood

-1.70

afety

-1.63

rika

-1.60

othing

-1.59

behavior

-1.52

 illusions

-1.51

POSITIVE LOGITS

 srfAttach

2.01

archive

1.87

catentry

1.79

intendent

1.60

 bidder

1.56

 pivot

1.49

vet

1.46

 threaten

1.44

 langu

1.44

 backdrop

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.